© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140169
    Prev
    Next
    INDEX
    Explanations

    activist defenders peace observatory

    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
    墘
    0.63
     cosas
    0.60
     advertise
    0.57
     ragazza
    0.57
     também
    0.56
     включают
    0.55
     dû
    0.55
     говорят
    0.55
     estadísticas
    0.55
     статистика
    0.55
    POSITIVE LOGITS
    hers
    0.60
    s
    0.57
    x
    0.56
     students
    0.56
     practitioners
    0.55
    unders
    0.55
    layout
    0.54
    ers
    0.54
     entrants
    0.54
    es
    0.53
    Activations Density 0.001%

    No Known Activations