© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13818
    Prev
    Next
    INDEX
    Explanations

    proper nouns representing organizations, brands, or locations

    oai_token-act-pair · gemini-2.0-flash

    Website snippets

    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
    vnd
    -0.39
    kund
    -0.39
     bek
    -0.39
    陷
    -0.39
    XMLSchema
    -0.39
    saga
    -0.38
    üb
    -0.38
     resourceCulture
    -0.37
    рь
    -0.37
    ins
    -0.36
    POSITIVE LOGITS
    toMatchSnapshot
    0.71
    niająca
    0.67
    windowFixed
    0.66
    WebVitals
    0.66
     typelib
    0.65
     ProtoMessage
    0.64
    pośred
    0.62
    IsMutable
    0.61
    enumii
    0.59
     betweenstory
    0.59
    Activations Density 2.190%

    No Known Activations