© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90264
    Prev
    Next
    INDEX
    Explanations

    create

    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_11_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
    LE
    0.43
     certificación
    0.42
    危険
    0.41
     \
    0.40
    ening
    0.39
    ↵
    0.38
     الاست
    0.38
     ограничения
    0.38
    轸
    0.37
    限定
    0.37
    POSITIVE LOGITS
    র
    0.38
    p
    0.37
    Ց
    0.36
    ttle
    0.35
    ר
    0.35
     doGet
    0.35
    rung
    0.35
    މ
    0.35
     gł
    0.34
    Dirty
    0.34
    Activations Density 0.020%

    No Known Activations