© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141349
    Prev
    Next
    INDEX
    Explanations

    Museum Island and Pergamon Museum

    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_12_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
    CIA
    0.52
     Մ
    0.52
     检测
    0.52
    द
    0.52
    憸
    0.52
    ξε
    0.52
    qPCR
    0.52
    äuser
    0.50
    થ
    0.50
     М
    0.49
    POSITIVE LOGITS
     toe
    0.57
     shark
    0.57
     lumber
    0.55
     blacksmith
    0.55
    unikasi
    0.53
     rudder
    0.52
     noodle
    0.52
     gua
    0.52
     tulang
    0.52
     restorations
    0.52
    Activations Density 0.001%

    No Known Activations