© 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. 133662
    Prev
    Next
    INDEX
    Explanations

    Shinichi Kimura Asada

    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
    <0x80>
    1.24
    一
    1.09
     That
    1.05
    you
    1.04
    、
    1.04
    that
    1.01
    g
    1.01
    ،
    1.01
    I
    0.99
    一脸
    0.96
    POSITIVE LOGITS
    ید
    1.27
     to
    1.17
    ção
    1.13
    یت
    1.09
    -
    1.09
     genes
    0.95
    ু
    0.95
    י
    0.93
     laureate
    0.92
    ہ
    0.92
    Activations Density 0.001%

    No Known Activations