© 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. 139137
    Prev
    Next
    INDEX
    Explanations

    MODULE_LICENSE

    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
     Acoustics
    0.41
     开
    0.38
    רוי
    0.38
    getPosition
    0.36
     प्रकोप
    0.36
    เว
    0.36
     рада
    0.36
     charters
    0.36
    вере
    0.35
    central
    0.35
    POSITIVE LOGITS
     país
    0.43
    CriteriaUtils
    0.40
     seh
    0.38
    Ⴀ
    0.37
     उम्र
    0.36
    iciable
    0.36
    usalem
    0.36
     inhibiting
    0.36
     translucent
    0.36
     Transparent
    0.36
    Activations Density 0.001%

    No Known Activations