© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217423
    Prev
    Next
    INDEX
    Explanations

    history and places

    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_50_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
     V
    0.50
    V
    0.49
    Volt
    0.41
    Grav
    0.40
    Vert
    0.39
     B
    0.39
    වු
    0.39
    lem
    0.39
    blatt
    0.39
    Полу
    0.38
    POSITIVE LOGITS
     kane
    0.44
     ዘ
    0.42
     ग्रैंड
    0.40
     concede
    0.38
     conceded
    0.38
    モニター
    0.38
    щенко
    0.38
     Kane
    0.37
     చేశారు
    0.37
     Geneva
    0.37
    Activations Density 0.001%

    No Known Activations