© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253735
    Prev
    Next
    INDEX
    Explanations

    cheer

    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
    ﻉ
    0.39
    Registre
    0.37
    样品
    0.37
     स्टूड
    0.36
     deur
    0.36
     Specified
    0.36
    aries
    0.36
    tevõ
    0.36
    ຸ
    0.36
    னம்
    0.35
    POSITIVE LOGITS
     leading
    1.23
    leading
    1.20
     Leading
    1.20
    Leading
    1.20
     веду
    1.04
    LEADING
    0.98
     dẫn
    0.83
     joht
    0.80
    веду
    0.78
    leader
    0.77
    Activations Density 0.000%

    No Known Activations