© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3986
    Prev
    Next
    INDEX
    Explanations

    references in the text, often indicated by bracketed numbers, "p." for page numbers, "note" for footnotes, the symbol "@", or the word "from"

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    page numbers/code locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.53
    InsertCommand
    -0.53
     propOrder
    -0.52
    исленность
    -0.47
     Car
    -0.47
    ian
    -0.47
    anten
    -0.46
    elemField
    -0.45
     Par
    -0.44
     SwitchCompat
    -0.44
    POSITIVE LOGITS
    onViewCreated
    0.66
     ModelExpression
    0.65
    érience
    0.64
    tvguidetime
    0.62
     caufe
    0.62
    Hochspringen
    0.60
     itſelf
    0.60
    WriteBarrier
    0.59
    pregunt
    0.58
     GetEnumerator
    0.56
    Activations Density 6.109%

    No Known Activations