© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210905
    Prev
    Next
    INDEX
    Explanations

    load instructions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     REGULATIONS
    0.45
    wood
    0.42
     produktów
    0.41
     ジャケット
    0.41
    WOOD
    0.39
    ollip
    0.39
    নির্ব
    0.39
    閾
    0.39
     regulations
    0.38
    ctl
    0.38
    POSITIVE LOGITS
    щите
    0.38
    Input
    0.38
     паро
    0.38
     Tons
    0.35
    珲
    0.35
    rinth
    0.34
    裘
    0.34
    தனை
    0.34
    राट
    0.34
    ⅝
    0.34
    Activations Density 0.001%

    No Known Activations