© 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. 6224
    Prev
    Next
    INDEX
    Explanations

    HTML artifacts and malformed formatting

    oai_token-act-pair · gemini-2.0-flash

    HTML and code 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_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
     Appearance
    -0.47
     Substitution
    -0.46
     Observation
    -0.46
     Extraction
    -0.46
     Morphology
    -0.45
     Utilisation
    -0.42
     Modification
    -0.42
     ContentValues
    -0.42
     autorytatywna
    -0.41
     degeneracy
    -0.41
    POSITIVE LOGITS
    ⓘ
    0.72
    исленность
    0.68
    ;
    0.65
    lamabad
    0.63
    _);
    0.59
    cings
    0.59
    $;
    0.59
    ;}
    0.58
    ’;
    0.57
    :✨
    0.57
    Activations Density 13.018%

    No Known Activations