© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 218255
    Prev
    Next
    INDEX
    Explanations

    meta charset

    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
    রার
    0.39
     authentic
    0.39
     Dirección
    0.38
     periodic
    0.38
    逄
    0.36
     bitte
    0.36
    ীরে
    0.36
    妘
    0.35
    луйста
    0.35
    转向
    0.35
    POSITIVE LOGITS
     नाय
    0.41
    पंजाब
    0.40
    bridge
    0.39
     ناخذ
    0.39
    map
    0.38
    FromBody
    0.37
    建設
    0.36
    Map
    0.36
     stamp
    0.36
    PL
    0.36
    Activations Density 0.000%

    No Known Activations