© 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. 155597
    Prev
    Next
    INDEX
    Explanations

    lack

    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
    Not in Any Lists

    No Comments

    Negative Logits
    today
    0.47
    will
    0.45
    time
    0.44
    stan
    0.44
    a
    0.44
    stoff
    0.43
    shops
    0.42
    stime
    0.42
     أحد
    0.41
    is
    0.41
    POSITIVE LOGITS
     Look
    0.59
     What
    0.54
     Size
    0.52
     Use
    0.50
     Kind
    0.50
    :
    0.48
     Given
    0.48
     Looking
    0.48
     You
    0.47
     Width
    0.47
    Activations Density 0.005%

    No Known Activations