© 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
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 213856
    Prev
    Next
    INDEX
    Explanations

    dates and periods

    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_47_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
    排
    0.42
     manpower
    0.38
    swf
    0.38
    严
    0.38
    }}}$
    0.38
     architekt
    0.38
     vyp
    0.37
     tiring
    0.37
    idik
    0.37
     pię
    0.37
    POSITIVE LOGITS
     Beaucoup
    0.39
     കാല
    0.39
     Lugo
    0.39
    Calcium
    0.38
    閲覧
    0.38
    கால
    0.38
    setKeepCallback
    0.38
    лец
    0.38
     Decade
    0.37
    襄
    0.37
    Activations Density 0.000%

    No Known Activations