© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79324
    Prev
    Next
    INDEX
    Explanations

    linux distro

    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
    在
    1.70
     in
    1.52
    لي
    1.45
    ع
    1.34
    t
    1.32
    大
    1.27
    на
    1.26
    ח
    1.26
    *}$
    1.23
    ط
    1.23
    POSITIVE LOGITS
    า
    1.87
    as
    1.56
    i
    1.54
    in
    1.51
    া
    1.49
    ে
    1.48
    ार
    1.40
    ா
    1.40
    ু
    1.35
    ar
    1.32
    Activations Density 0.000%

    No Known Activations