© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221130
    Prev
    Next
    INDEX
    Explanations

    DFA

    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_10_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
    ália
    0.52
     νη
    0.49
    ɬ
    0.48
     ド
    0.46
     comma
    0.46
     الجم
    0.45
    鮪
    0.45
    CRET
    0.45
    ulates
    0.44
    悪
    0.44
    POSITIVE LOGITS
    0
    0.57
    Forest
    0.47
    adz
    0.44
    гово
    0.43
    लिंग
    0.43
    投影
    0.43
    дентификаторы
    0.43
    2
    0.42
    }
    0.42
    derive
    0.42
    Activations Density 0.000%

    No Known Activations