© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8847
    Prev
    Next
    INDEX
    Explanations

    and (listing examples)

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italian
    0.44
     Finnish
    0.43
     Japanese
    0.43
    urized
    0.42
     daran
    0.41
    '
    0.41
    phenol
    0.41
    ensi
    0.41
    venida
    0.41
    nya
    0.40
    POSITIVE LOGITS
    N
    0.49
    ෲ
    0.45
    สำหรับการ
    0.44
     veröffentlicht
    0.44
     femelles
    0.43
    ９
    0.41
    🗒
    0.41
    SPECIAL
    0.40
     femelle
    0.40
     spéciaux
    0.40
    Activations Density 0.055%

    No Known Activations