© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39914
    Prev
    Next
    INDEX
    Explanations

    Avogadro, chemical elements, Greek letters

    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_3_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
    IN
    0.90
    ない
    0.85
     paralelo
    0.84
     grueling
    0.81
     temos
    0.79
     arī
    0.78
    ES
    0.78
     rápido
    0.76
     lento
    0.76
    મ
    0.76
    POSITIVE LOGITS
    '
    1.16
    c
    0.79
    ق
    0.74
    th
    0.68
    cyt
    0.61
    ↵
    0.59
    h
    0.59
    чина
    0.59
    к
    0.59
    st
    0.58
    Activations Density 0.005%

    No Known Activations