© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54706
    Prev
    Next
    INDEX
    Explanations

    times

    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_31_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
     high
    0.48
     aspir
    0.42
    เล
    0.41
     risk
    0.38
    influ
    0.38
    estone
    0.37
     chief
    0.36
    high
    0.36
    炡
    0.36
     tiger
    0.36
    POSITIVE LOGITS
    ジア
    0.37
    LogIn
    0.36
    CBPeripheral
    0.36
    PARAMS
    0.36
     கட்டமை
    0.35
    僧
    0.35
     میکرز
    0.34
    NCR
    0.33
    0.33
    日閲覧
    0.33
    Activations Density 0.000%

    No Known Activations