© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14102
    Prev
    Next
    INDEX
    Explanations

    dates and numbered quantities

    oai_token-act-pair · gemini-2.0-flash

    beginnings and endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    principalColumn
    -0.63
    esModule
    -0.60
    principalTable
    -0.56
    ProcessEvent
    -0.56
    UnsafeEnabled
    -0.55
    LError
    -0.55
     AspNetCore
    -0.54
     endgül
    -0.54
    BindingResult
    -0.53
    makeText
    -0.52
    POSITIVE LOGITS
    "]];
    0.61
    "]="
    0.60
     виправивши
    0.59
     obstante
    0.58
     rowspan
    0.55
    )];
    0.55
     CascadeType
    0.54
    )}</
    0.54
    ovács
    0.53
     ')[
    0.52
    Activations Density 17.281%

    No Known Activations