© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235641
    Prev
    Next
    INDEX
    Explanations

    NSF

    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
    креп
    0.43
     DRAM
    0.40
    dil
    0.39
    ქმ
    0.39
    cru
    0.38
    куль
    0.37
    Collabor
    0.37
    █
    0.36
    ceq
    0.36
    ಕ್ಷಣ
    0.35
    POSITIVE LOGITS
     laure
    0.39
     Tuition
    0.38
    िके
    0.38
    Office
    0.37
     விஞ்ஞான
    0.37
     riferimento
    0.37
     étendue
    0.37
    鍍
    0.37
     lấy
    0.37
     nặng
    0.37
    Activations Density 0.000%

    No Known Activations