© 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. 41256
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
    ed
    0.26
    red
    0.24
    il
    0.23
     diper
    0.23
    ind
    0.23
    ad
    0.22
    ↵↵↵
    0.22
    fe
    0.22
    ext
    0.21
    aking
    0.21
    POSITIVE LOGITS
     ২০২১
    0.21
    ombi
    0.21
     SYSTEMS
    0.21
     будут
    0.20
    сово
    0.20
     mouseY
    0.20
     систем
    0.20
     socialists
    0.20
     ransomware
    0.20
    ండే
    0.19
    Activations Density 0.003%

    No Known Activations