© 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. 221221
    Prev
    Next
    INDEX
    Explanations

    call for

    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
    열
    0.42
    㸳
    0.40
     Vuk
    0.38
    ⓑ
    0.38
    シオ
    0.37
     첨
    0.37
     remote
    0.37
     mba
    0.36
    oinette
    0.36
    antiates
    0.36
    POSITIVE LOGITS
    品
    0.41
    几天
    0.38
    (".");
    0.38
    ̨
    0.37
     CQG
    0.36
    ifice
    0.36
    pector
    0.35
     reprezent
    0.35
     ત્યાર
    0.35
    ائط
    0.35
    Activations Density 0.002%

    No Known Activations