© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22114
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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_56_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
     derr
    0.42
     लेट्स
    0.39
     deth
    0.37
    LoginPage
    0.37
    рей
    0.37
     tos
    0.36
    老爷
    0.35
     忄
    0.35
    மார்க்
    0.35
    เทียบ
    0.35
    POSITIVE LOGITS
     অনুস
    0.44
     goed
    0.40
     gre
    0.39
    Zeit
    0.38
    graduate
    0.37
    وانات
    0.37
     wenig
    0.37
     serial
    0.36
    Graduate
    0.35
    serial
    0.35
    Activations Density 0.000%

    No Known Activations