© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136351
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
     Му
    0.53
    ﻤ
    0.51
     Մ
    0.48
    ﺘ
    0.47
     بيد
    0.46
     СА
    0.46
    ﺜ
    0.45
     ನ
    0.44
     Ри
    0.44
     Ρ
    0.44
    POSITIVE LOGITS
    Kron
    0.50
    {
    0.45
    cro
    0.45
    เวลา
    0.44
     वक़्त
    0.43
    $
    0.42
     Kron
    0.42
     $\$
    0.41
     vuoden
    0.40
    exp
    0.39
    Activations Density 0.000%

    No Known Activations