© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216596
    Prev
    Next
    INDEX
    Explanations

    put into

    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_31_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
    捪
    0.39
    㖷
    0.38
     Msg
    0.36
     (${
    0.36
     भंग
    0.35
    blind
    0.34
     fodder
    0.34
     मोहन
    0.34
    interested
    0.34
    coding
    0.34
    POSITIVE LOGITS
     મુજબ
    0.37
     उतार
    0.36
     منع
    0.35
     obey
    0.35
    ძლიათ
    0.35
    ushi
    0.34
    榫
    0.34
    Paulo
    0.34
    achi
    0.33
    aktoren
    0.33
    Activations Density 0.002%

    No Known Activations