© 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. 142424
    Prev
    Next
    INDEX
    Explanations

    graph networks, power laws

    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_12_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
    *
    0.55
     de
    0.52
     techn
    0.52
     оборудования
    0.52
    <
    0.51
     series
    0.50
    &
    0.50
     collab
    0.49
     business
    0.49
     académ
    0.49
    POSITIVE LOGITS
    panelMenuList
    0.54
    ujjati
    0.52
    评分
    0.49
    GING
    0.49
     pictureBox
    0.48
     पुस्तिका
    0.48
    </i>
    0.48
    ிருக்கு
    0.47
     "\\"
    0.47
    Fhir
    0.46
    Activations Density 0.001%

    No Known Activations