© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 100
    Prev
    Next
    INDEX
    Explanations

    programming keywords (`function`, `const`)

    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_40_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
    צא
    0.43
    Chip
    0.38
    }|\
    0.38
     そんな
    0.38
     पुरी
    0.38
    imerick
    0.37
    utip
    0.37
    ضاء
    0.36
     ज्ञा
    0.36
    🥩
    0.36
    POSITIVE LOGITS
     remove
    0.40
     barrier
    0.38
    decorate
    0.37
     déc
    0.36
     decorations
    0.35
     parabol
    0.34
     Amos
    0.34
     decorated
    0.34
     decorator
    0.34
    BFS
    0.34
    Activations Density 0.007%

    No Known Activations