© 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. 122180
    Prev
    Next
    INDEX
    Explanations

    Gustavo, Eiffel, Guava, Petro

    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
     然而
    0.74
    。「
    0.66
     einiger
    0.65
    ф
    0.65
    .,
    0.64
     Pero
    0.64
     Рабо
    0.61
     sonidos
    0.61
    BackgroundHelper
    0.60
    림픽
    0.60
    POSITIVE LOGITS
    s
    1.09
    ς
    0.84
    ের
    0.80
    es
    0.79
    ed
    0.79
    אם
    0.73
    ی
    0.69
    ாக
    0.67
    ת
    0.66
    m
    0.66
    Activations Density 0.000%

    No Known Activations