© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53394
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_55_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
    ﻒ
    0.41
     চায়
    0.37
     esperienze
    0.37
    کٹ
    0.36
    лга
    0.35
    ั้ย
    0.35
    ㄆ
    0.35
     хочется
    0.34
    ındadır
    0.34
    тою
    0.34
    POSITIVE LOGITS
    //
    0.44
    orb
    0.41
    inu
    0.41
    ;;
    0.39
    //}
    0.39
     Feminist
    0.39
    var
    0.38
     —
    0.38
    window
    0.38
    String
    0.37
    Activations Density 0.003%

    No Known Activations