© 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. 257256
    Prev
    Next
    INDEX
    Explanations

    defines command-line flags

    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
    jvm
    0.48
     democratic
    0.42
     socials
    0.42
    ດີ
    0.42
    pd
    0.41
    democratic
    0.40
    <code>
    0.40
     fandom
    0.39
    腧
    0.38
     tass
    0.38
    POSITIVE LOGITS
     irritated
    0.42
     chuyển
    0.41
     aprox
    0.41
     inició
    0.40
     fecha
    0.40
     vinculado
    0.40
    ็อก
    0.40
    ^{*},
    0.40
    して
    0.39
    悩
    0.39
    Activations Density 0.000%

    No Known Activations