© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228882
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ሓ
    0.39
    ToDelete
    0.38
    emde
    0.37
    aspect
    0.36
    [*
    0.35
    लेज
    0.34
    dering
    0.34
     służ
    0.33
    extensive
    0.33
    ⤷
    0.33
    POSITIVE LOGITS
     Bring
    0.42
    ிறேன்
    0.40
    ந்தது
    0.39
     Cliffs
    0.39
    რება
    0.39
    ثة
    0.38
    𒌑
    0.38
     கொண்டு
    0.38
    nju
    0.37
    oría
    0.37
    Activations Density 0.000%

    No Known Activations