© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257254
    Prev
    Next
    INDEX
    Explanations

    preview Composable UI elements

    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_22_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
    Ờ
    0.38
     ্
    0.35
    čních
    0.34
    Ẳ
    0.34
    oviruses
    0.34
    erk
    0.32
    ALWAYS
    0.32
    yue
    0.32
    ovali
    0.31
    ophyllum
    0.31
    POSITIVE LOGITS
     ('
    0.38
    無
    0.37
    ีย
    0.37
    SourceName
    0.34
     Pulitzer
    0.33
    Metall
    0.32
     Metall
    0.32
     भूप
    0.32
     दुबई
    0.32
    損
    0.32
    Activations Density 0.000%

    No Known Activations