© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31926
    Prev
    Next
    INDEX
    Explanations

    s fashion or thereon

    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_7_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
     for
    0.54
    س
    0.42
    说
    0.41
     at
    0.40
     and
    0.39
    ní
    0.38
    ス
    0.37
     absences
    0.36
     be
    0.36
     as
    0.36
    POSITIVE LOGITS
    ра
    0.37
    и
    0.28
    Chứng
    0.27
     Masyarakat
    0.26
     I
    0.25
    या
    0.25
    Into
    0.25
    Time
    0.25
    ре
    0.25
     John
    0.25
    Activations Density 0.003%

    No Known Activations