© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40101
    Prev
    Next
    INDEX
    Explanations

    PE

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     Джо
    0.37
    resident
    0.36
    調べて
    0.36
    喬
    0.36
     penultimate
    0.36
     joe
    0.35
    kab
    0.35
     functie
    0.35
    akwa
    0.34
    乔
    0.34
    POSITIVE LOGITS
     และ
    0.39
    ;/
    0.37
     προσ
    0.36
     ហើយ
    0.36
     ident
    0.35
    ;-
    0.35
    لے
    0.34
    Utils
    0.34
     Payment
    0.34
     Utils
    0.33
    Activations Density 0.031%

    No Known Activations