© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51034
    Prev
    Next
    INDEX
    Explanations

    databases and sqlite

    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
     ው
    0.42
    ium
    0.40
     Conferences
    0.40
     Wind
    0.39
     Conference
    0.39
    чает
    0.39
    isał
    0.38
     يوجد
    0.38
     Property
    0.38
     znak
    0.38
    POSITIVE LOGITS
    誇
    0.36
     gate
    0.35
     رضا
    0.34
     moyen
    0.34
     ಉತ್ತ
    0.33
    RIG
    0.33
     //-
    0.33
     arranger
    0.33
    nable
    0.33
    ματο
    0.33
    Activations Density 0.000%

    No Known Activations