© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2771
    Prev
    Next
    INDEX
    Explanations

    snippets of words or phrases that might be related to editing or modifying text or code

    oai_token-act-pair · gemini-2.0-flash

    tokens related to content attributes

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

    Programming related text

    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
     estekak
    -0.60
    ValueStyle
    -0.50
     huyền
    -0.46
    principalTable
    -0.43
    Ellips
    -0.42
    這位
    -0.40
     ordf
    -0.39
     Pfar
    -0.39
    XtraEditors
    -0.38
     everybody
    -0.38
    POSITIVE LOGITS
     EconPapers
    0.81
    ArrowToggle
    0.66
    brainly
    0.63
    RunAsync
    0.59
     незавершена
    0.58
    Rüyada
    0.57
    EndContext
    0.57
    multer
    0.56
     jScrollPane
    0.56
    Tembelea
    0.56
    Activations Density 0.133%

    No Known Activations