© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14388
    Prev
    Next
    INDEX
    Explanations

    inverse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     eTo
    0.56
     devem
    0.55
    ronomie
    0.55
    sstream
    0.55
    🕘
    0.55
     demais
    0.53
     дина
    0.53
    ナソニック
    0.52
     dovuto
    0.52
    ってます
    0.52
    POSITIVE LOGITS
     (
    0.53
    این
    0.53
    д
    0.52
    າດ
    0.50
    ینی
    0.49
    ᆷ
    0.49
    יין
    0.48
    திய
    0.48
    ਤ
    0.48
    ﻗ
    0.48
    Activations Density 0.034%

    No Known Activations