© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149972
    Prev
    Next
    INDEX
    Explanations

    upload

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     Waits
    0.43
    ropical
    0.43
     cae
    0.41
     Wat
    0.41
     Approve
    0.40
     Wait
    0.39
    „
    0.39
     Wel
    0.39
     Prove
    0.38
     Did
    0.38
    POSITIVE LOGITS
    IT
    0.42
     ROW
    0.38
     TEXT
    0.37
     ఉ
    0.37
    it
    0.37
    AMA
    0.36
     IT
    0.36
     ഒന്ന
    0.36
     GUN
    0.36
     IM
    0.35
    Activations Density 0.000%

    No Known Activations