© 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. 208459
    Prev
    Next
    INDEX
    Explanations

    column identifiers

    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
    KEYDOWN
    0.42
    DeleteDialogOpen
    0.42
    </caption>
    0.39
     AGAIN
    0.38
    Farland
    0.38
     ストレ
    0.38
    鄰
    0.37
     <!
    0.37
     INCLUDING
    0.36
    DLJ
    0.36
    POSITIVE LOGITS
    imenti
    0.39
    ment
    0.39
    uciones
    0.39
    inicial
    0.39
    전자
    0.39
    device
    0.39
    ments
    0.38
    antib
    0.38
     الوطنية
    0.38
    인은
    0.38
    Activations Density 0.001%

    No Known Activations