© 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. 228661
    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
     THE
    0.37
    {"
    0.37
     Power
    0.37
     Château
    0.37
     चेहरे
    0.36
    とい
    0.36
     ஆய
    0.36
     Phương
    0.36
     Berl
    0.35
     Theodor
    0.35
    POSITIVE LOGITS
    autoref
    0.40
    ppage
    0.38
    ambuf
    0.38
    steller
    0.37
    rmap
    0.37
    㹮
    0.36
    phases
    0.36
    ppable
    0.35
    ittäin
    0.35
    closer
    0.35
    Activations Density 0.000%

    No Known Activations