© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121404
    Prev
    Next
    INDEX
    Explanations

    code initialization and configuration

    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_38_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
     фо
    0.36
     තර
    0.36
    شته
    0.33
    IFO
    0.33
    Alignment
    0.33
     idéale
    0.33
     ተ
    0.33
    pract
    0.33
    โท
    0.33
    urazione
    0.33
    POSITIVE LOGITS
    永
    0.43
     Phrases
    0.40
     NATIONAL
    0.39
    經濟
    0.38
     national
    0.38
    national
    0.38
     Needham
    0.38
     Joining
    0.37
    導致
    0.37
     federal
    0.37
    Activations Density 0.000%

    No Known Activations