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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50275
    Prev
    Next
    INDEX
    Explanations

    event, guest, dress, round

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     мәкалә
    0.43
    ග
    0.43
     Diaspora
    0.41
    华人
    0.39
    遥
    0.39
    崖
    0.38
     রাজধান
    0.38
     phytochemical
    0.38
     Володимир
    0.37
    遙
    0.37
    POSITIVE LOGITS
    pol
    0.39
     сель
    0.37
     Grange
    0.37
    NLS
    0.36
    Pol
    0.36
     EPI
    0.36
    ABE
    0.35
     crumpled
    0.35
    GRE
    0.34
     বিবি
    0.34
    Activations Density 0.016%

    No Known Activations