© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4885
    Prev
    Next
    INDEX
    Explanations

    myself, you, feel, want

    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_39_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
    ෝජ
    0.39
     Bucc
    0.38
     आंसू
    0.36
    念
    0.35
    複合
    0.35
    感受
    0.35
     bistouri
    0.35
     missed
    0.34
     scoprire
    0.34
     கண்ண
    0.34
    POSITIVE LOGITS
     admit
    0.44
     Admit
    0.39
    Adm
    0.39
     ലഭ
    0.38
     ಹೊಂದ
    0.37
    ಡುವುದ
    0.37
     admitting
    0.36
     token
    0.35
    wnież
    0.35
    ބ
    0.35
    Activations Density 0.144%

    No Known Activations