© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122805
    Prev
    Next
    INDEX
    Explanations

    how do you

    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_37_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
    ؟
    0.45
     Ex
    0.39
    澈
    0.39
     Installer
    0.38
    ?"
    0.38
     ?";
    0.37
    Ex
    0.36
    ?
    0.36
    ?",
    0.35
     ؟
    0.35
    POSITIVE LOGITS
    .”)
    0.45
    你想
    0.45
    你要
    0.39
    あなたの
    0.39
     wanna
    0.39
     loop
    0.38
    解決
    0.38
    想
    0.38
     pformat
    0.38
    应
    0.38
    Activations Density 0.003%

    No Known Activations