© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141830
    Prev
    Next
    INDEX
    Explanations

    executive administrative path

    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_0_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
     I
    1.98
     as
    1.88
    أ
    1.72
    2
    1.52
    3
    1.44
     by
    1.39
    ты
    1.35
    ه
    1.30
    ات
    1.29
    as
    1.28
    POSITIVE LOGITS
    ま
    1.31
    ח
    1.30
     ایران
    1.15
     ปลา
    1.14
    lerin
    1.13
    多い
    1.12
     ili
    1.10
     کند
    1.10
    িন
    1.09
    li
    1.09
    Activations Density 0.000%

    No Known Activations