© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16247
    Prev
    Next
    INDEX
    Explanations

    code snippets with URLs and references to web technologies

    oai_token-act-pair · gemini-2.0-flash

    /

    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
    ----</
    -0.57
    KommentareTeilen
    -0.48
    ValueGeneration
    -0.44
     ingen
    -0.42
    MigrationBuilder
    -0.42
     adelant
    -0.42
    clip
    -0.41
     frem
    -0.40
    atchewan
    -0.40
     SHOWING
    -0.40
    POSITIVE LOGITS
    BeginContext
    0.77
    saraba
    0.68
    例句
    0.65
    <bos>
    0.62
     Roskov
    0.61
     Infórmanos
    0.59
     firebaseConfig
    0.59
    CloseOperation
    0.58
     kaarangay
    0.58
     strtotime
    0.57
    Activations Density 8.325%

    No Known Activations