© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31099
    Prev
    Next
    INDEX
    Explanations

    crisis, especially followed by context or "Text"

    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_7_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
     be
    1.16
    س
    1.15
     a
    1.07
    م
    1.02
    is
    1.00
    de
    0.97
    f
    0.95
     to
    0.95
     the
    0.93
    S
    0.93
    POSITIVE LOGITS
     giocatore
    0.80
     anciens
    0.79
     الذي
    0.77
     giocatori
    0.76
     achet
    0.75
     earners
    0.74
    RENCY
    0.73
     systemu
    0.73
     anciennes
    0.72
     hérit
    0.72
    Activations Density 0.003%

    No Known Activations