© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14211
    Prev
    Next
    INDEX
    Explanations

    Mrs. Davison, Clara, Her, She

    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_15_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
    _{*}(
    0.22
     FIXED
    0.22
     دھو
    0.22
    وريا
    0.22
    㐫
    0.22
     ваши
    0.21
    vaegir
    0.21
     ધ્યાન
    0.21
     Scholz
    0.21
     все
    0.21
    POSITIVE LOGITS
    in
    0.26
    leck
    0.22
    rig
    0.21
    lis
    0.21
    afat
    0.20
    ----------------
    0.20
    latitude
    0.20
    bins
    0.20
    list
    0.20
    bu
    0.20
    Activations Density 0.019%

    No Known Activations