© 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. 257268
    Prev
    Next
    INDEX
    Explanations

    empty or layout

    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
    ÖR
    0.42
     краї
    0.42
    ொருள்
    0.41
    పార్
    0.40
    odimensional
    0.39
    ੋਰ
    0.38
     Burj
    0.37
    낮
    0.37
     posizione
    0.37
    餐廳
    0.36
    POSITIVE LOGITS
     Pain
    0.48
     Rip
    0.43
     Undo
    0.43
     Identities
    0.41
    으
    0.41
     RIP
    0.41
     Directly
    0.41
     Beth
    0.41
    arnya
    0.41
     painless
    0.41
    Activations Density 0.000%

    No Known Activations