© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138659
    Prev
    Next
    INDEX
    Explanations

    use prelude or entity

    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
    ”
    0.63
     S
    0.59
     of
    0.59
    -
    0.58
     woman
    0.53
    ↵
    0.53
     ous
    0.53
     D
    0.52
     tomar
    0.52
     director
    0.52
    POSITIVE LOGITS
     حصہ
    0.62
    ড়যন্ত্র
    0.61
     ایکسپریس
    0.58
    entliche
    0.57
    ortic
    0.56
    ーン
    0.54
    gunta
    0.53
    缙
    0.53
    ILERS
    0.53
    никова
    0.53
    Activations Density 0.001%

    No Known Activations