© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 101625
    Prev
    Next
    INDEX
    Explanations

    Enter

    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_44_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    挑战
    0.41
    fraction
    0.36
    勇
    0.36
    Mys
    0.35
     stopwords
    0.35
     допомогою
    0.34
    melt
    0.34
    érm
    0.34
    stopwords
    0.34
     শব্দ
    0.34
    POSITIVE LOGITS
     shell
    0.40
    cije
    0.38
     Shell
    0.37
     shells
    0.37
     VW
    0.36
     pieces
    0.36
    ⵣ
    0.36
     reasons
    0.36
    setView
    0.36
    icycle
    0.35
    Activations Density 0.001%

    No Known Activations