© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88711
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ס
    0.74
    та
    0.73
    ла
    0.73
    のカ
    0.71
     план
    0.70
     причины
    0.70
     dolorem
    0.69
    );}
    0.69
    کل
    0.67
    с
    0.67
    POSITIVE LOGITS
    ل
    1.04
    l
    1.03
    r
    0.87
    h
    0.82
    n
    0.79
    al
    0.78
    t
    0.77
    one
    0.76
    ions
    0.75
    d
    0.71
    Activations Density 0.000%

    No Known Activations