© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205489
    Prev
    Next
    INDEX
    Explanations

    units of length (inch, cm)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    те
    0.69
     wasteful
    0.63
     sépt
    0.63
     digamos
    0.62
     tế
    0.62
    愘
    0.61
     hấp
    0.59
     говоря
    0.58
     réforme
    0.58
     séptimo
    0.57
    POSITIVE LOGITS
    h
    0.86
    m
    0.75
    v
    0.71
     p
    0.64
    0.64
    व
    0.63
    ap
    0.63
    و
    0.63
    انية
    0.61
    alunos
    0.59
    Activations Density 0.009%

    No Known Activations