© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178541
    Prev
    Next
    INDEX
    Explanations

    SQL and code 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_24_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
    忔
    0.40
    shaped
    0.38
    願
    0.38
    HARAD
    0.37
     हां
    0.37
     വര്‍
    0.37
    作為
    0.36
    ทะ
    0.36
     நடு
    0.36
    স্থিত
    0.36
    POSITIVE LOGITS
     route
    0.41
     automotive
    0.39
     watered
    0.39
     breed
    0.38
     choral
    0.38
     wider
    0.37
    쯤
    0.36
     beyond
    0.36
     brethren
    0.36
     poured
    0.35
    Activations Density 0.000%

    No Known Activations