© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39879
    Prev
    Next
    INDEX
    Explanations

    comfort and ease

    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_11_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
    o
    0.91
    m
    0.64
    ac
    0.60
    ad
    0.58
    و
    0.58
    AN
    0.57
    f
    0.55
    AU
    0.52
    s
    0.52
    au
    0.51
    POSITIVE LOGITS
    습니다
    0.58
    ObjData
    0.52
    ī
    0.52
    <unused202>
    0.52
     струк
    0.51
     berichten
    0.51
    лизм
    0.51
    ,”
    0.50
    ிகள்
    0.50
     Roya
    0.50
    Activations Density 0.009%

    No Known Activations