© 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. 40021
    Prev
    Next
    INDEX
    Explanations

    French basic words

    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
     venus
    0.42
     fe
    0.37
     boy
    0.37
     merits
    0.36
    auff
    0.35
    ધુ
    0.35
    ሻ
    0.35
    avut
    0.35
     cpp
    0.35
     authorize
    0.34
    POSITIVE LOGITS
     levers
    0.38
     Ruh
    0.38
    quel
    0.37
     usk
    0.37
    🆗
    0.36
    Sqrt
    0.36
     ROUT
    0.35
    Channel
    0.35
    Jessica
    0.34
     Jessica
    0.34
    Activations Density 0.002%

    No Known Activations