© 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. 54373
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
    Not in Any Lists

    No Comments

    Negative Logits
    перыі
    0.40
     ಅದರ
    0.35
    ющийся
    0.34
    痿
    0.34
     Вікі
    0.34
     variational
    0.33
    ScriptInterface
    0.33
    ፉ
    0.33
     фунда
    0.32
     ἡ
    0.32
    POSITIVE LOGITS
    inio
    0.39
    studio
    0.37
     bial
    0.36
    pias
    0.36
     svolge
    0.35
     roller
    0.35
    hate
    0.35
     leave
    0.35
    Pov
    0.34
    essage
    0.34
    Activations Density 0.050%

    No Known Activations