© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45283
    Prev
    Next
    INDEX
    Explanations

    sovereignty

    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_13_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
    uch
    0.56
    ud
    0.55
    UD
    0.54
    ul
    0.50
     திரும்பி
    0.50
    UNCH
    0.50
    腑
    0.50
    UND
    0.49
    Pump
    0.49
    USH
    0.47
    POSITIVE LOGITS
     obeying
    0.53
     telefoon
    0.53
     volgens
    0.52
     sobri
    0.51
     meth
    0.50
     confidentialité
    0.50
    ᱪ
    0.50
     acquitted
    0.49
     docile
    0.49
     cilvē
    0.49
    Activations Density 0.000%

    No Known Activations