© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15035
    Prev
    Next
    INDEX
    Explanations

    statements related to general facts and figures, and being in existence

    oai_token-act-pair · gemini-2.0-flash

    negative situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     виправивши
    -0.92
    IntoConstraints
    -0.84
     Мексичка
    -0.84
     HasFactory
    -0.82
    存于互联网档案馆
    -0.82
    SharedCtor
    -0.82
    Portály
    -0.81
    Datuak
    -0.81
    EDEFAULT
    -0.77
    complexContent
    -0.75
    POSITIVE LOGITS
     at
    0.46
     as
    0.42
     At
    0.40
    ili
    0.39
    prox
    0.38
    At
    0.37
     其
    0.36
    Most
    0.35
    とは
    0.34
    ള
    0.34
    Activations Density 3.053%

    No Known Activations