© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141654
    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_0_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
     be
    1.47
     I
    1.39
     the
    1.23
     effusion
    1.21
     it
    1.20
     to
    1.18
     в
    1.09
     \
    1.08
    k
    1.05
     interrog
    1.03
    POSITIVE LOGITS
    ت
    2.09
    т
    1.91
    ר
    1.76
    م
    1.71
    お
    1.65
    ী
    1.63
    大
    1.63
    at
    1.59
    ع
    1.58
    ע
    1.58
    Activations Density 0.000%

    No Known Activations