© 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. 228883
    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
     nine
    0.37
    <0xBF>
    0.35
     Nine
    0.35
    õi
    0.35
     எனப்படும்
    0.34
    َوْ
    0.32
     snapshots
    0.32
     अस्थ
    0.32
     creep
    0.32
     staple
    0.32
    POSITIVE LOGITS
    Associ
    0.40
    咄
    0.37
     ASSOCI
    0.36
    associ
    0.35
    ስቃ
    0.33
     வேண்டு
    0.33
    Gerald
    0.32
     Associ
    0.32
     UIColor
    0.32
     第
    0.31
    Activations Density 0.000%

    No Known Activations