© 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. 14454
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for figures and document formatting.

    oai_token-act-pair · gemini-2.0-flash

    code and documentation

    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
    이터
    -0.38
    osho
    -0.35
    $',
    -0.35
    ();*/
    -0.35
    êque
    -0.35
    });*/
    -0.34
     al
    -0.34
    NAL
    -0.34
     P
    -0.34
     שוליים
    -0.34
    POSITIVE LOGITS
    richTextPanel
    0.72
    awtextra
    0.71
    المناصب
    0.67
     Cortez
    0.66
     ſind
    0.63
     biber
    0.63
    Legenda
    0.63
    contentLoaded
    0.63
     vane
    0.62
    keyColumn
    0.62
    Activations Density 2.402%

    No Known Activations