© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65013
    Prev
    Next
    INDEX
    Explanations

    cyber

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     ን
    0.39
     linguistique
    0.39
     حص
    0.39
     التر
    0.38
     තුළ
    0.38
     hampers
    0.38
     Bren
    0.36
    𝐩
    0.36
     arz
    0.36
    طلاع
    0.36
    POSITIVE LOGITS
    kill
    0.45
     kill
    0.43
    war
    0.43
     war
    0.40
    Historia
    0.39
    attack
    0.38
    વાર
    0.38
    ीट
    0.38
    Sep
    0.38
    郡
    0.38
    Activations Density 0.002%

    No Known Activations