© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154634
    Prev
    Next
    INDEX
    Explanations

    from right to left

    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_23_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
    꺾
    0.40
    সকল
    0.39
     Wählen
    0.39
     Dislocations
    0.39
    VIAF
    0.38
     convolutions
    0.38
     взя
    0.38
     đều
    0.37
    ège
    0.37
     decoración
    0.37
    POSITIVE LOGITS
    tain
    0.42
    sdk
    0.37
    payroll
    0.36
     ***",
    0.35
    <th>
    0.35
     brine
    0.35
    lin
    0.34
    territ
    0.34
    height
    0.34
     wasn
    0.34
    Activations Density 0.001%

    No Known Activations