© 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. 122019
    Prev
    Next
    INDEX
    Explanations

    magic mirror

    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
    watt
    0.39
    >\<
    0.39
     केशव
    0.39
    খিল
    0.38
    strup
    0.37
     diving
    0.37
    showAlert
    0.37
    ╹
    0.36
     breezes
    0.35
    🔺
    0.35
    POSITIVE LOGITS
     obice
    0.43
     Ums
    0.38
     Hath
    0.38
    ট্র
    0.38
    assic
    0.37
    遺跡
    0.37
    iev
    0.37
     দত্ত
    0.36
    Sal
    0.36
    聸
    0.35
    Activations Density 0.000%

    No Known Activations