© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199602
    Prev
    Next
    INDEX
    Explanations

    css grid columns

    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_12_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
     Wird
    0.52
    ダー
    0.52
    AY
    0.51
     Peace
    0.49
     ICC
    0.46
     اولى
    0.46
     Theta
    0.46
    ై
    0.46
     tongue
    0.45
     or
    0.45
    POSITIVE LOGITS
    glazed
    0.55
    水口
    0.54
    मील
    0.54
    վ
    0.52
    Chloe
    0.52
     rén
    0.51
     sklep
    0.50
    エム
    0.50
    馥
    0.50
    γκ
    0.50
    Activations Density 0.002%

    No Known Activations