© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210350
    Prev
    Next
    INDEX
    Explanations

    UPLOAD_FOLDER, SECRET_KEY

    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_19_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
     sábado
    0.43
    ζο
    0.42
    怜
    0.42
    ūn
    0.41
     joyous
    0.40
     fiyat
    0.39
     жүктөп
    0.39
     메서
    0.39
    pleasant
    0.39
    MaxPooling
    0.39
    POSITIVE LOGITS
     Butt
    0.55
     Dadurch
    0.53
    洙
    0.49
     Textbook
    0.49
     butt
    0.48
    ಡಿ
    0.48
     lake
    0.48
     आईं
    0.44
     Sides
    0.44
    Criminal
    0.44
    Activations Density 0.000%

    No Known Activations