© 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. 167293
    Prev
    Next
    INDEX
    Explanations

    cleanser

    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
     платформа
    0.37
    フォー
    0.36
    衵
    0.36
     дре
    0.36
     Py
    0.36
    Py
    0.36
     এলিট
    0.35
    bakan
    0.35
    峈
    0.35
    shops
    0.35
    POSITIVE LOGITS
    ClearedBy
    0.38
     Walden
    0.38
    UCI
    0.38
     Thoreau
    0.37
     moldings
    0.37
     Tasting
    0.37
    uche
    0.37
     لوا
    0.37
    uc
    0.36
     fau
    0.36
    Activations Density 0.002%

    No Known Activations