© 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. 229368
    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
    kta
    0.46
    
    0.37
    ሉ።
    0.36
     па
    0.36
     Preschool
    0.35
     Invention
    0.34
    ))*(
    0.34
     biscuit
    0.34
     ఏ
    0.33
    ర్టు
    0.33
    POSITIVE LOGITS
    inken
    0.41
    ჯ
    0.41
    JA
    0.39
    reon
    0.39
    virt
    0.39
     JA
    0.39
     lan
    0.38
    enged
    0.38
    vio
    0.38
     এটাও
    0.38
    Activations Density 0.000%

    No Known Activations