© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252408
    Prev
    Next
    INDEX
    Explanations

    Stealth

    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_56_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
    hid
    0.42
    hened
    0.40
    h
    0.39
    hi
    0.39
    хід
    0.39
    снов
    0.38
    HID
    0.38
    ჰ
    0.38
    ส่
    0.37
    хода
    0.37
    POSITIVE LOGITS
     th
    1.09
     Th
    1.09
    Th
    1.04
     الث
    0.84
     TH
    0.84
     थ
    0.79
     ธ
    0.70
     Thal
    0.70
    TH
    0.69
     ث
    0.69
    Activations Density 0.002%

    No Known Activations