© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4031
    Prev
    Next
    INDEX
    Explanations

    words containing "mal", "tos", or "titis", and words ending in "-ting", "ics", or "ian"

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    expandindo
    -0.96
    دانشنامهٔ
    -0.85
    MigrationBuilder
    -0.82
     mergeFrom
    -0.80
    mybatisplus
    -0.77
     فريبيس
    -0.76
    RenderAtEndOf
    -0.75
     ویکی‌پدیای
    -0.72
     propOrder
    -0.72
    RegressionTest
    -0.71
    POSITIVE LOGITS
     rett
    0.55
     thư
    0.54
    ztat
    0.50
     متعلقه
    0.48
    chelles
    0.48
     Malta
    0.48
    NgModule
    0.47
    taobao
    0.47
     Mal
    0.47
     chile
    0.47
    Activations Density 0.542%

    No Known Activations