© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4668
    Prev
    Next
    INDEX
    Explanations

    parts of academic citations

    oai_token-act-pair · gemini-2.0-flash

    Academic publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ArgsConstructor
    -0.58
    存于互联网档案馆
    -0.56
    djangoproject
    -0.52
     yii
    -0.50
     препратки
    -0.48
     min
    -0.47
     зато
    -0.47
     ch
    -0.47
    AndEndTag
    -0.47
     si
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.71
    يميديا
    0.59
    reeg
    0.57
    posedge
    0.57
    batore
    0.56
    TypedDataSet
    0.56
    viewWillAppear
    0.55
     Independ
    0.55
     وتسجيلات
    0.52
    XMLSchema
    0.52
    Activations Density 0.486%

    No Known Activations