© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8267
    Prev
    Next
    INDEX
    Explanations

    code related to charts and graphs

    oai_token-act-pair · gemini-2.0-flash

    programming charts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     chart
    -2.03
     Chart
    -1.99
     charts
    -1.95
    chart
    -1.85
    Chart
    -1.83
     CHART
    -1.79
     Charts
    -1.79
    CHART
    -1.66
    charts
    -1.63
    Charts
    -1.55
    POSITIVE LOGITS
    ngrx
    0.59
    __).
    0.57
     Ause
    0.55
     NgModule
    0.54
    resave
    0.52
    TextWatcher
    0.51
    ɵɵelementStart
    0.51
     ويكيپيديا
    0.51
    WebServlet
    0.50
    linearGradient
    0.50
    Activations Density 1.915%

    No Known Activations