© 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. 13926
    Prev
    Next
    INDEX
    Explanations

    a variety of related acronyms, possibly from academic papers or software

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms

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

    Code snippets

    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
    ⓧ
    -0.88
    möglichkeiten
    -0.68
    Література
    -0.65
    upply
    -0.62
    hared
    -0.61
    cito
    -0.60
    uccess
    -0.60
    hape
    -0.60
     насељу
    -0.60
    SourceChecksum
    -0.58
    POSITIVE LOGITS
     onAnimation
    0.56
    DataAnnotations
    0.51
    Alike
    0.46
    
    0.43
    quedas
    0.43
    RUnlock
    0.42
     envy
    0.42
    ByPrimaryKey
    0.41
     Wiktionnaire
    0.41
    RAF
    0.40
    Activations Density 2.061%

    No Known Activations