© 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. 52967
    Prev
    Next
    INDEX
    Explanations

    welcomed, popular, liked

    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
    TIA
    0.40
     overwritten
    0.38
     hus
    0.37
    ndor
    0.37
    壯
    0.36
     Hus
    0.36
     researchers
    0.35
    सील
    0.35
    mart
    0.35
     economist
    0.35
    POSITIVE LOGITS
    Обра
    0.40
    gebung
    0.35
     modulo
    0.35
     좋아
    0.34
    ЕР
    0.34
    爱
    0.34
    兴趣
    0.34
     관심을
    0.34
     કારણ
    0.34
     almak
    0.33
    Activations Density 0.001%

    No Known Activations