© 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. 228749
    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
    ofs
    0.43
    ALS
    0.42
    refs
    0.38
    Ven
    0.38
    嘯
    0.38
    mitt
    0.37
    OMS
    0.37
    angels
    0.37
    ADS
    0.36
     relato
    0.36
    POSITIVE LOGITS
     centric
    0.41
     modest
    0.39
     n
    0.38
     octane
    0.38
     voilà
    0.37
     abond
    0.37
     নেন
    0.36
    <0xB8>
    0.35
    ibut
    0.35
     splen
    0.35
    Activations Density 0.000%

    No Known Activations