© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199962
    Prev
    Next
    INDEX
    Explanations

    inode number

    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_15_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
    St
    0.48
    StartZ
    0.44
    乙
    0.42
    SEM
    0.41
    HZ
    0.41
    ఎఫ్
    0.41
    2
    0.40
    D
    0.40
    ST
    0.40
    γκα
    0.40
    POSITIVE LOGITS
     URLs
    0.45
     Barça
    0.45
     eBay
    0.45
     atraer
    0.43
    遒
    0.43
     Mom
    0.42
     Mussolini
    0.42
     và
    0.42
     അതിന്റെ
    0.42
    been
    0.42
    Activations Density 0.002%

    No Known Activations