© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11370
    Prev
    Next
    INDEX
    Explanations

    sentences in formal writing that provide context or support a statement.

    oai_token-act-pair · gemini-2.0-flash

    words related to relativity

    np_token-act-pair-logits · gpt-4o-mini

    articles "a" and "an"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ThemeOverlay
    -0.50
     funny
    -0.46
     Occidente
    -0.45
    ngan
    -0.44
     funniest
    -0.43
    blad
    -0.43
    нень
    -0.43
    ok
    -0.42
    MLLoader
    -0.41
    łada
    -0.41
    POSITIVE LOGITS
     مشين
    0.84
    providedIn
    0.69
    ContentAsync
    0.69
    relatively
    0.65
     متعلقه
    0.62
     relatively
    0.62
     chi̍t
    0.61
    EndProject
    0.60
    WireFormatLite
    0.60
     relativamente
    0.60
    Activations Density 4.498%

    No Known Activations