© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13783
    Prev
    Next
    INDEX
    Explanations

    application class, accelerating, squeaky

    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_15_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
    ...*/
    0.54
     ಒಂದು
    0.52
    ETARY
    0.52
     monkey
    0.51
    ವುದ
    0.50
     prepend
    0.49
    ofthe
    0.49
    Ꮃ
    0.49
    ANDER
    0.48
     hyg
    0.48
    POSITIVE LOGITS
    ge
    0.53
    går
    0.49
    ogr
    0.49
    Patients
    0.49
    gr
    0.47
    生
    0.47
    girl
    0.47
    garden
    0.46
    patients
    0.46
    ்டர்
    0.46
    Activations Density 0.000%

    No Known Activations