© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123118
    Prev
    Next
    INDEX
    Explanations

    soy sauce

    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_3_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
    ה
    0.75
    이다
    0.68
     എന്നാൽ
    0.66
    ம
    0.63
    ری
    0.63
     của
    0.63
    ิน
    0.62
    その
    0.60
    がいる
    0.59
     nerveux
    0.59
    POSITIVE LOGITS
    ans
    0.78
    í
    0.77
    x
    0.76
    z
    0.69
    ä
    0.69
    s
    0.68
    ných
    0.67
    sp
    0.66
    nk
    0.66
    ha
    0.66
    Activations Density 0.000%

    No Known Activations