© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81930
    Prev
    Next
    INDEX
    Explanations

    empowering

    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_0_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
     are
    1.67
    are
    1.67
    4
    1.60
    0
    1.57
    9
    1.55
     as
    1.53
    ;
    1.50
    ot
    1.49
    8
    1.43
    1
    1.41
    POSITIVE LOGITS
    Z
    1.49
    K
    1.28
    H
    1.25
    V
    1.23
    ת
    1.22
    X
    1.20
    W
    1.20
    T
    1.16
    Q
    1.16
    ט
    1.14
    Activations Density 0.001%

    No Known Activations