Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14579
    Prev
    Next
    INDEX
    Explanations

    image file names and numbers

    oai_token-act-pair · gemini-2.0-flash

    URLs and image references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    criptures
    -0.49
     bổ
    -0.47
    archiviato
    -0.45
     đề
    -0.44
     ex
    -0.43
    antası
    -0.43
     Point
    -0.42
    стандарт
    -0.42
     mwenye
    -0.40
    져
    -0.40
    POSITIVE LOGITS
     فريبيس
    0.81
    ="@+
    0.77
     LUMP
    0.73
     itſelf
    0.73
    DoubleQuotes
    0.71
     houſe
    0.71
    RenderAtEndOf
    0.71
     raiſ
    0.71
    verwijspagina
    0.71
     ModelExpression
    0.69
    Activations Density 2.085%

    No Known Activations