© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130277
    Prev
    Next
    INDEX
    Explanations

    огромный

    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_1_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
    س
    0.95
    of
    0.89
    ট
    0.88
    jela
    0.88
    ier
    0.87
     đạo
    0.87
    viii
    0.87
    ole
    0.86
    с
    0.86
    含ま
    0.84
    POSITIVE LOGITS
    the
    1.21
    و
    1.04
    ка
    1.01
    il
    0.98
    ↵
    0.94
    τή
    0.93
    us
    0.92
    ल
    0.91
    нің
    0.88
    没有
    0.87
    Activations Density 0.000%

    No Known Activations