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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85586
    Prev
    Next
    INDEX
    Explanations

    regular expressions and numbers

    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_23_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
     merupakan
    0.42
    ContentAlignment
    0.40
    ੍ਰ
    0.39
    ှ
    0.37
    ̴
    0.37
    ୟ
    0.36
    Shadow
    0.36
    ,—
    0.36
    LEC
    0.36
    堤
    0.36
    POSITIVE LOGITS
     draining
    0.41
     cuatro
    0.39
     ছুট
    0.38
    陖
    0.38
    ర్లు
    0.38
     czerw
    0.37
     televisión
    0.37
     television
    0.37
     بتاعت
    0.37
     indag
    0.36
    Activations Density 0.002%

    No Known Activations