© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100120
    Prev
    Next
    INDEX
    Explanations

    Anaconda installation and distribution

    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_14_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
    ":"
    0.54
    üşt
    0.54
    ()}
    0.46
    ORY
    0.46
    $(".
    0.46
    هور
    0.46
    ؛
    0.45
     protest
    0.45
     risult
    0.44
    ;"
    0.44
    POSITIVE LOGITS
     सच्चा
    0.64
    lių
    0.57
    टिंग
    0.56
     роско
    0.55
     स्थापना
    0.54
     Lust
    0.54
    ガラス
    0.54
     নিখ
    0.53
     何
    0.52
     پیسې
    0.52
    Activations Density 0.002%

    No Known Activations