© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33863
    Prev
    Next
    INDEX
    Explanations

    People's Government, Congress, Bank, PeoplePerHour

    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_3_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
    ä
    0.98
    ong
    0.84
    ü
    0.83
    い
    0.80
    im
    0.79
    em
    0.78
    W
    0.77
    os
    0.76
    of
    0.76
    ons
    0.74
    POSITIVE LOGITS
     pás
    0.63
     acus
    0.60
     rů
    0.60
     evidente
    0.60
     σχέ
    0.59
    敛
    0.59
     collectiv
    0.59
     данни
    0.59
     équipes
    0.58
     kteří
    0.58
    Activations Density 0.003%

    No Known Activations