© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176284
    Prev
    Next
    INDEX
    Explanations

    Ra

    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_50_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
     Ross
    0.47
     Smit
    0.40
     管
    0.40
     Spi
    0.40
    Ross
    0.38
     gent
    0.37
    ]$;
    0.36
     ву
    0.36
     Glas
    0.36
    гни
    0.36
    POSITIVE LOGITS
    aud
    0.44
    ichen
    0.43
    ABAB
    0.43
    withdrawal
    0.43
    withdraw
    0.40
    HTree
    0.39
    dala
    0.39
     withdrawing
    0.38
     Withdrawal
    0.38
     öner
    0.38
    Activations Density 0.001%

    No Known Activations