© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12856
    Prev
    Next
    INDEX
    Explanations

    scientific or procedural words and phrases often found in scientific papers.

    oai_token-act-pair · gemini-2.0-flash

    food and product consumption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Personendaten
    -0.66
    mappedBy
    -0.66
    WebVitals
    -0.64
     незавершена
    -0.63
    DoubleQuotes
    -0.62
    wikidata
    -0.58
    tvguidetime
    -0.58
    )++;
    -0.57
    ngdoc
    -0.56
     ComVisible
    -0.54
    POSITIVE LOGITS
     Anſ
    0.56
    answer
    0.54
     Auff
    0.52
     Theſe
    0.51
     greateſt
    0.48
     ſtand
    0.48
     professionally
    0.48
    دانشنامهٔ
    0.46
     Diſ
    0.46
     présidentielle
    0.46
    Activations Density 0.602%

    No Known Activations