© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102120
    Prev
    Next
    INDEX
    Explanations

    assumption or bargaining

    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_14_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
     productions
    0.55
     líneas
    0.53
    FileSync
    0.52
     Productions
    0.51
    avorable
    0.51
     theres
    0.51
     Rios
    0.50
    >∞</
    0.50
     economists
    0.50
     Espíritu
    0.49
    POSITIVE LOGITS
     т
    0.68
     waar
    0.55
    ला
    0.54
     انا
    0.54
    la
    0.52
    如果你
    0.51
    iyasi
    0.50
     一
    0.49
    ın
    0.48
     isten
    0.47
    Activations Density 0.000%

    No Known Activations