© 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. 228854
    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
    를
    2.72
    を
    2.30
     را
    2.11
    을
    2.11
    ளில்
    1.47
    ını
    1.45
    ನ್ನು
    1.35
    ને
    1.29
    ကို
    1.19
    க்கு
    1.15
    POSITIVE LOGITS
    ሁን
    0.45
    ુ
    0.42
    ಿವೆ
    0.41
    ისუფ
    0.40
    ሁ
    0.39
    tingen
    0.39
    광역시
    0.35
    强烈
    0.35
    ୁ
    0.34
    irrahim
    0.34
    Activations Density 0.000%

    No Known Activations