© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137723
    Prev
    Next
    INDEX
    Explanations

    system related terms

    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
    drž
    0.41
     Pred
    0.39
    RAJ
    0.39
    끗
    0.38
    CONTACT
    0.38
     correspondences
    0.38
    黼
    0.37
    <unused73>
    0.37
    されていた
    0.37
    pred
    0.36
    POSITIVE LOGITS
     compito
    0.40
     task
    0.39
     современ
    0.38
     ~(~)
    0.38
     زمان
    0.37
     स्वर्ण
    0.37
    ͙
    0.37
     productive
    0.36
    ヱ
    0.36
    чности
    0.36
    Activations Density 0.000%

    No Known Activations