© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196721
    Prev
    Next
    INDEX
    Explanations

    impact

    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_46_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
     pé
    0.45
     analý
    0.40
     زمانی
    0.39
     ava
    0.39
    ទំន
    0.38
    朋
    0.38
     modernize
    0.37
     probabilidades
    0.37
    ✞
    0.37
    AVI
    0.37
    POSITIVE LOGITS
     חלק
    0.44
    రుపు
    0.38
    helpers
    0.37
     部分
    0.37
    asius
    0.37
    Increase
    0.35
    altern
    0.35
    increase
    0.35
    それに
    0.35
     নিষ্প
    0.35
    Activations Density 0.003%

    No Known Activations