© 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. 194412
    Prev
    Next
    INDEX
    Explanations

    1099 forms

    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
    čen
    0.54
     बचने
    0.53
     charming
    0.50
     सतर्क
    0.50
    ્યારે
    0.50
     dahil
    0.49
    י
    0.49
     mencari
    0.49
     silent
    0.49
     accountant
    0.49
    POSITIVE LOGITS
    زاء
    0.52
     தவ
    0.50
    维修
    0.49
    ασ
    0.48
    영화
    0.47
    Few
    0.46
    Total
    0.46
     defeats
    0.46
     Total
    0.46
    '));
    0.45
    Activations Density 0.002%

    No Known Activations