© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5641
    Prev
    Next
    INDEX
    Explanations

    parts of the document where questions/answers, places, travel, and debate are taking place.

    oai_token-act-pair · gemini-2.0-flash

    Plus signs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     brancas
    -0.71
     vermelhas
    -0.69
    ⃣
    -0.57
     prêts
    -0.51
     popolare
    -0.51
     titolata
    -0.51
     sanitaires
    -0.49
     ©️
    -0.49
    &
    -0.47
     seguras
    -0.46
    POSITIVE LOGITS
     +
    1.99
    +
    1.53
     '+
    1.49
     $+$
    1.48
     $+
    1.47
     "+
    1.45
     +
    1.37
     + 
    1.32
    '+
    1.31
    "+
    1.29
    Activations Density 6.659%

    No Known Activations