© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 76837
    Prev
    Next
    INDEX
    Explanations

    M

    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_53_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
    alle
    0.42
    Morgan
    0.41
    Rs
    0.39
    R
    0.38
    adis
    0.37
    adhi
    0.37
    rs
    0.37
    rH
    0.37
    吸
    0.36
    вка
    0.36
    POSITIVE LOGITS
     Se
    0.44
    Se
    0.42
     SE
    0.41
     패
    0.41
    patri
    0.40
    se
    0.40
     Liqu
    0.39
    BtnPanel
    0.38
    .??.??"]
    0.38
     se
    0.38
    Activations Density 0.006%

    No Known Activations