© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26716
    Prev
    Next
    INDEX
    Explanations

    Hannah Arendt, Susan Sontag, Harry Frankfurt, Laura Mulvey

    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_40_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
    ♗
    0.38
     Surve
    0.37
    ylen
    0.37
    дун
    0.36
     hours
    0.36
     glaciers
    0.35
     anodic
    0.34
     Ist
    0.34
    ócio
    0.34
    észeti
    0.34
    POSITIVE LOGITS
    ochlor
    0.39
    作業
    0.37
    iphenyl
    0.37
    成
    0.36
    нях
    0.36
    相同
    0.36
     डीएनए
    0.35
    レポート
    0.35
    عمال
    0.35
    ்த்து
    0.35
    Activations Density 0.000%

    No Known Activations