© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83296
    Prev
    Next
    INDEX
    Explanations

    antigens

    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
     by
    1.45
     for
    1.34
    0
    1.30
    is
    1.30
     I
    1.25
     {})
    1.25
     By
    1.18
     _)
    1.17
     inade
    1.13
     been
    1.11
    POSITIVE LOGITS
    s
    1.80
    d
    1.80
    ,
    1.69
    ने
    1.46
    er
    1.40
    д
    1.38
    UM
    1.29
    ка
    1.22
    ς
    1.20
    る
    1.20
    Activations Density 0.000%

    No Known Activations