© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64549
    Prev
    Next
    INDEX
    Explanations

    `#include` directives and `.h` files

    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_41_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
    Positive
    0.42
    쏠
    0.41
    POSITIVE
    0.39
     fountains
    0.37
     positive
    0.37
    positive
    0.36
     positivo
    0.36
     પોલી
    0.35
    Chick
    0.35
    ESTER
    0.35
    POSITIVE LOGITS
     Transcription
    0.41
    杪
    0.40
     header
    0.39
    メディア
    0.38
     tabs
    0.38
     StatusBar
    0.38
    本発明
    0.38
     じゃん
    0.37
     पंकज
    0.37
    tabs
    0.37
    Activations Density 0.002%

    No Known Activations