© 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. 252642
    Prev
    Next
    INDEX
    Explanations

    say "e" words

    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
    kont
    0.40
    aring
    0.39
    kot
    0.38
    時間を
    0.38
    एस्ट
    0.38
    挺
    0.38
    startTimestamp
    0.37
    ITING
    0.36
    itting
    0.35
    ിലേ
    0.35
    POSITIVE LOGITS
    ﻀ
    0.42
     Pros
    0.39
    chman
    0.39
    SWITCH
    0.38
    omponent
    0.38
    bangan
    0.37
    ضو
    0.37
    erunner
    0.37
    CCA
    0.37
     pros
    0.35
    Activations Density 0.000%

    No Known Activations