© 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. 198083
    Prev
    Next
    INDEX
    Explanations

    simple random sampling

    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
    Squares
    0.37
    Square
    0.34
    áj
    0.34
    𝑺
    0.34
    Area
    0.32
    Organization
    0.31
    hci
    0.31
    Fa
    0.31
    community
    0.31
     सर्विसेज
    0.31
    POSITIVE LOGITS
     treacherous
    0.43
     sinister
    0.41
     booted
    0.39
     slimy
    0.39
     ventricular
    0.38
     snugly
    0.37
     ر
    0.37
     ב
    0.36
     troublesome
    0.36
     insidious
    0.36
    Activations Density 0.001%

    No Known Activations