© 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. 149673
    Prev
    Next
    INDEX
    Explanations

    for

    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
     Helping
    0.45
     Stopping
    0.42
     ஒன்றை
    0.40
     schedule
    0.40
    tembre
    0.39
     epoxide
    0.39
     hit
    0.39
    мата
    0.39
    )"><
    0.38
     hari
    0.38
    POSITIVE LOGITS
    flag
    0.82
    Flag
    0.80
    FLAG
    0.70
     so
    0.64
     Flag
    0.64
     flag
    0.59
     picking
    0.57
    flags
    0.57
    那麼
    0.54
    Flags
    0.52
    Activations Density 0.001%

    No Known Activations