© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 94140
    Prev
    Next
    INDEX
    Explanations

    Rock

    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_60_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
     aten
    0.45
     সালে
    0.43
     auctor
    0.43
     empfohlen
    0.41
     ат
    0.40
     rezerv
    0.39
     lontano
    0.39
     representantes
    0.38
     zoek
    0.38
    ງ
    0.38
    POSITIVE LOGITS
    in
    0.99
    ing
    0.55
    port
    0.54
    top
    0.52
    inį
    0.52
    sta
    0.51
    inl
    0.50
    station
    0.49
    inud
    0.49
    to
    0.48
    Activations Density 0.000%

    No Known Activations