© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156545
    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_2_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
    '
    1.66
     was
    1.55
    ’
    1.51
    of
    1.30
     and
    1.27
    KS
    1.16
    =
    1.14
    :
    1.14
     de
    1.13
    ']
    1.13
    POSITIVE LOGITS
    م
    1.61
    را
    1.57
    ла
    1.44
    ور
    1.33
    기
    1.30
    ס
    1.26
    ند
    1.19
    ва
    1.17
    ет
    1.16
    ش
    1.16
    Activations Density 0.000%

    No Known Activations