© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126603
    Prev
    Next
    INDEX
    Explanations

    registered trademark symbols and brands

    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_37_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
    stern
    0.38
     ʼ
    0.37
    elier
    0.36
    oticons
    0.36
    дина
    0.36
    ʼ
    0.35
    揆
    0.35
    דה
    0.34
    ভেদ
    0.34
    </img>
    0.34
    POSITIVE LOGITS
    ®
    1.57
     ®
    1.43
    ®,
    1.37
    ®.
    1.34
     ™
    1.18
    ™
    1.17
     trademark
    1.12
    Ⓡ
    1.09
    ™,
    1.07
     trademarks
    1.04
    Activations Density 0.002%

    No Known Activations