© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219981
    Prev
    Next
    INDEX
    Explanations

    material and language encoding

    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
     হৈ
    0.36
    ಮ್
    0.35
     airing
    0.35
     సినీ
    0.34
     soph
    0.32
    Soph
    0.32
     DIRE
    0.32
    追
    0.32
    Dire
    0.31
    灰色
    0.31
    POSITIVE LOGITS
     matériaux
    0.41
     материалы
    0.38
     materials
    0.35
     Bahan
    0.35
     материалов
    0.34
     konzent
    0.34
    frank
    0.34
     المواد
    0.33
    varlak
    0.33
     fluid
    0.33
    Activations Density 0.002%

    No Known Activations