© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 145008
    Prev
    Next
    INDEX
    Explanations

    racer or raced

    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
     a
    2.14
    t
    1.88
    c
    1.67
    li
    1.60
    ли
    1.51
     are
    1.45
    ta
    1.39
    pt
    1.36
    ll
    1.36
    mn
    1.35
    POSITIVE LOGITS
    し
    1.71
    P
    1.58
    H
    1.53
    न
    1.52
    น
    1.52
    ע
    1.48
    The
    1.45
    นาง
    1.45
    Y
    1.44
    Α
    1.44
    Activations Density 0.000%

    No Known Activations