© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257133
    Prev
    Next
    INDEX
    Explanations

    column width adjust

    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_22_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
    Boolean
    0.48
    保有
    0.46
    IN
    0.46
    ಭ
    0.44
    인
    0.42
    ното
    0.42
    িসহ
    0.41
    庄
    0.41
    原来
    0.38
    ιν
    0.38
    POSITIVE LOGITS
     learning
    0.53
     monarchs
    0.47
    ،
    0.46
     director
    0.46
     azimuthal
    0.46
     aerodynamics
    0.45
     Learning
    0.45
     handbags
    0.44
     apocalypse
    0.44
     handling
    0.43
    Activations Density 0.000%

    No Known Activations