© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241076
    Prev
    Next
    INDEX
    Explanations

    square root

    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_25_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
    辨
    0.42
    अधिक
    0.40
     મહિના
    0.37
     इसकी
    0.37
    pedo
    0.37
    gob
    0.36
     संपर्क
    0.36
     aplicativo
    0.36
    nuevo
    0.36
    व्हाण
    0.36
    POSITIVE LOGITS
     IGBT
    0.37
    謝
    0.37
    Fg
    0.36
    📷
    0.36
    /−
    0.36
     sheaf
    0.35
     descent
    0.35
    ולוג
    0.35
    ∇
    0.35
    МІ
    0.34
    Activations Density 0.000%

    No Known Activations