© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15539
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming related terms

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     snippetHide
    -2.73
    
    -2.63
    DockStyle
    -2.63
    tvguidetime
    -2.59
    providedIn
    -2.58
     مشين
    -2.42
    AndEndTag
    -2.42
    ConstraintMaker
    -2.42
    IntoConstraints
    -2.38
     ModelExpression
    -2.34
    POSITIVE LOGITS
    namefont
    0.69
     itſelf
    0.64
    SimpleName
    0.60
     purpoſe
    0.58
     subsequent
    0.56
     themſelves
    0.56
    ícone
    0.56
    madrid
    0.55
     theils
    0.55
    miot
    0.53
    Activations Density 2.620%

    No Known Activations