© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81292
    Prev
    Next
    INDEX
    Explanations

    string literal closing bracket

    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_31_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
     tetrachloride
    0.20
    encil
    0.20
    rombin
    0.20
    沇
    0.20
    रीन
    0.19
    aratus
    0.19
    法语
    0.18
     пери
    0.18
    狭
    0.18
     Seal
    0.18
    POSITIVE LOGITS
     erfahren
    0.21
     hosszú
    0.21
     longues
    0.21
    कर्
    0.20
     dénom
    0.19
    endir
    0.19
     erzählen
    0.19
     interess
    0.19
     emoz
    0.18
    eroom
    0.18
    Activations Density 0.005%

    No Known Activations