© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39626
    Prev
    Next
    INDEX
    Explanations

    peanut butter and jelly

    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_11_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
    Đ
    0.50
    ेड
    0.50
    Punjab
    0.49
    ICAGO
    0.48
    ِيم
    0.45
    യിൽ
    0.44
    며
    0.44
    િંગ
    0.44
     ಕ್ಷೇತ್ರ
    0.44
     Đ
    0.43
    POSITIVE LOGITS
    iment
    0.58
    ukk
    0.58
    such
    0.55
     suche
    0.55
     tonal
    0.52
     solvable
    0.51
     simplifying
    0.50
     adaption
    0.50
    if
    0.49
     meio
    0.49
    Activations Density 0.028%

    No Known Activations