© 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. 204675
    Prev
    Next
    INDEX
    Explanations

    header and logo structure

    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
    市
    0.44
    Inject
    0.43
    imab
    0.42
     stalwart
    0.40
    idential
    0.39
    Style
    0.38
     inject
    0.38
    approve
    0.37
    ordeaux
    0.36
    invalid
    0.36
    POSITIVE LOGITS
    ‴
    0.39
     حلقات
    0.39
     алу
    0.38
    pike
    0.37
    ⬇
    0.37
     Calyce
    0.37
    ຄ້າ
    0.36
     tage
    0.36
     eğer
    0.36
     питания
    0.36
    Activations Density 0.001%

    No Known Activations