© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103876
    Prev
    Next
    INDEX
    Explanations

    entire followed by noun

    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_1_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
    ků
    1.19
    k
    1.15
    B
    1.14
    ли
    1.13
    aj
    1.11
    ك
    1.07
    R
    1.06
    kého
    1.02
    L
    1.02
    H
    1.01
    POSITIVE LOGITS
     जो
    0.96
    in
    0.90
     писа
    0.88
    >
    0.85
    to
    0.83
     וב
    0.81
    .
    0.80
     जिनके
    0.78
     を
    0.78
     forne
    0.78
    Activations Density 0.000%

    No Known Activations