© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3398
    Prev
    Next
    INDEX
    Explanations

    text encased within HTML span tags with a style attribute including "small-caps"

    oai_token-act-pair · gemini-2.0-flash

    caps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Biôgrafia
    -0.85
    migrationBuilder
    -0.82
    انيف
    -0.81
     Wicidata
    -0.81
    complexType
    -0.75
    tagHelperRunner
    -0.75
    出版年
    -0.74
     kaarangay
    -0.74
    الإنجليزية
    -0.73
    providedIn
    -0.73
    POSITIVE LOGITS
    setVerticalGroup
    0.47
    phoria
    0.41
    <bos>
    0.41
    Facades
    0.40
     relaxation
    0.39
     called
    0.38
     ria
    0.36
     instead
    0.36
     breath
    0.35
    Instead
    0.35
    Activations Density 2.366%

    No Known Activations