© 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
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 228892
    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
    砰
    0.40
    Lapangan
    0.38
    렐
    0.37
    Signup
    0.36
     Backdrop
    0.35
    ধি
    0.34
     видно
    0.34
    のア
    0.34
     Indices
    0.34
     promu
    0.34
    POSITIVE LOGITS
     tala
    0.43
    say
    0.39
     ar
    0.39
     really
    0.38
    枷
    0.38
    hander
    0.37
    roller
    0.37
    caesar
    0.37
    ijima
    0.37
     say
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.