© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198582
    Prev
    Next
    INDEX
    Explanations

    H

    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_46_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
     תש
    0.42
    HH
    0.40
    bhl
    0.39
    <0x97>
    0.38
     ಹ
    0.38
     HCM
    0.37
     хі
    0.37
    yh
    0.37
     hiệp
    0.37
    edal
    0.37
    POSITIVE LOGITS
    蚯
    0.41
    diagnostic
    0.40
    oden
    0.40
    verm
    0.38
     paralelas
    0.38
    offensive
    0.38
     इलेक्ट्रॉन
    0.38
     denominador
    0.37
     Oak
    0.37
    igrams
    0.37
    Activations Density 0.003%

    No Known Activations