© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38992
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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_57_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
    rared
    0.37
     डाटा
    0.37
    getitem
    0.35
    בד
    0.34
     театр
    0.34
    Recovery
    0.33
    bore
    0.33
    텟
    0.33
    दरी
    0.33
    贈り物
    0.33
    POSITIVE LOGITS
     เฉ
    0.42
     प्रि
    0.41
    ouna
    0.41
     расти
    0.41
     Poir
    0.39
     Willow
    0.38
     الصف
    0.38
    ∘
    0.37
    芎
    0.37
     okun
    0.37
    Activations Density 0.006%

    No Known Activations