© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9011
    Prev
    Next
    INDEX
    Explanations

    US politicians by name and state

    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
     gamanam
    0.33
    Databaze
    0.33
     +(
    0.31
    (",");
    0.31
     znamen
    0.30
     フラ
    0.30
     gunfire
    0.30
     neke
    0.29
     йөкләү
    0.29
     Regul
    0.29
    POSITIVE LOGITS
    在这种
    0.34
     cyberpunk
    0.32
     giusto
    0.31
     financière
    0.30
     ayant
    0.29
    ivist
    0.28
    ↵
    0.28
    yles
    0.28
     experts
    0.28
    ীরা
    0.27
    Activations Density 0.001%

    No Known Activations