© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202115
    Prev
    Next
    INDEX
    Explanations

    aseptic technique, Aseprite, isekai

    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_6_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
    c
    1.34
    (
    1.09
    ется
    1.06
    \
    0.99
    '
    0.98
    েল
    0.97
     traduc
    0.92
    ش
    0.91
     initialize
    0.91
    crist
    0.91
    POSITIVE LOGITS
    on
    1.30
    at
    1.25
    won
    0.99
    のス
    0.99
    in
    0.97
    ings
    0.97
    %)
    0.96
    ุ
    0.95
    words
    0.93
    he
    0.93
    Activations Density 0.000%

    No Known Activations