© 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. 53988
    Prev
    Next
    INDEX
    Explanations

    being in motion

    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
    searchResults
    0.37
    Claim
    0.36
     Lan
    0.36
    }>\
    0.36
    杩
    0.35
    }<\
    0.35
    льными
    0.34
     ["[
    0.34
    Though
    0.34
    nými
    0.34
    POSITIVE LOGITS
     सामान्य
    0.40
    কাণ্ড
    0.37
     পূর্ববাংলা
    0.37
     оконча
    0.37
    తర
    0.36
     கதாபா
    0.36
    全新的
    0.36
     fopen
    0.36
     совме
    0.36
     കഴ
    0.35
    Activations Density 0.002%

    No Known Activations