© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46233
    Prev
    Next
    INDEX
    Explanations

    business, technical, and educational contexts

    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_13_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
    🔪
    0.49
     Subhanahu
    0.49
    ▦
    0.49
     Babu
    0.47
     Prozesse
    0.47
     vVertex
    0.47
    multiSelectList
    0.46
     REACTORS
    0.46
    ³,
    0.46
     ентитету
    0.45
    POSITIVE LOGITS
    รถ
    0.54
    تد
    0.53
    '
    0.50
    込
    0.49
    માં
    0.46
     gym
    0.46
    dos
    0.46
    ના
    0.46
     filing
    0.45
     trich
    0.45
    Activations Density 0.000%

    No Known Activations