© 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. 122472
    Prev
    Next
    INDEX
    Explanations

    Cosmic Microwave Background

    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
    ة
    0.89
    байд
    0.69
     Bhosle
    0.65
    er
    0.64
    uves
    0.64
    gladbach
    0.64
    ing
    0.63
    بوع
    0.62
    kében
    0.61
    는데
    0.61
    POSITIVE LOGITS
     on
    1.02
     for
    0.91
     from
    0.87
     in
    0.80
     On
    0.66
    ल
    0.66
     with
    0.66
    dır
    0.66
     ON
    0.65
    好吃
    0.65
    Activations Density 0.000%

    No Known Activations