© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82120
    Prev
    Next
    INDEX
    Explanations

    cuffs

    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_0_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
    ก
    2.14
    ä
    1.80
    т
    1.48
    áme
    1.46
    ת
    1.42
    ز
    1.38
    ين
    1.37
    ü
    1.35
    ного
    1.32
    á
    1.31
    POSITIVE LOGITS
    i
    2.31
    in
    2.23
    a
    2.08
     as
    1.86
    to
    1.66
    ে
    1.65
    as
    1.64
     or
    1.61
     a
    1.53
     to
    1.49
    Activations Density 0.000%

    No Known Activations