© 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. 134911
    Prev
    Next
    INDEX
    Explanations

    aversiveness, averaging, Duda

    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
    ना
    0.90
    पी
    0.87
    ut
    0.79
    СТИ
    0.77
    ur
    0.75
    。
    0.75
    ясплат
    0.75
    ジ
    0.74
    ：
    0.73
    urm
    0.73
    POSITIVE LOGITS
     is
    1.48
    -
    1.13
     has
    1.01
    L
    0.99
    ita
    0.98
     Presidente
    0.98
    тся
    0.97
     I
    0.93
    schule
    0.93
     U
    0.91
    Activations Density 0.000%

    No Known Activations