© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228390
    Prev
    Next
    INDEX
    Explanations

    Coast

    np_max-act-logits · gemini-2.5-flash-lite
    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
    gee
    0.43
     Orphans
    0.41
    igin
    0.38
    ্টা
    0.38
    岐
    0.38
    Ign
    0.37
    ৃহে
    0.37
    orgt
    0.37
    夜
    0.36
    遮
    0.36
    POSITIVE LOGITS
     guard
    1.85
     Guard
    1.80
     gard
    1.80
    Gard
    1.76
     Gard
    1.73
    Guard
    1.71
    guard
    1.65
    gard
    1.62
     गार्ड
    1.59
     GUARD
    1.55
    Activations Density 0.001%

    No Known Activations