© 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-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261196
    Prev
    Next
    INDEX
    Explanations

    step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    1.55
    ک
    1.27
    ب
    1.27
    ু
    1.25
    $>
    1.20
    л
    1.17
    $
    1.13
    א
    1.12
    ש
    1.12
    );*/
    1.10
    POSITIVE LOGITS
    park
    1.05
    h
    1.04
    nv
    1.01
    group
    1.00
    jär
    1.00
    p
    1.00
    order
    1.00
    ní
    0.99
    a
    0.99
    under
    0.98
    Activations Density 0.000%

    No Known Activations