© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109250
    Prev
    Next
    INDEX
    Explanations

    iva, Riva, wa

    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_2_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
    ش
    1.49
    n
    1.48
     for
    1.36
    ند
    1.36
    is
    1.25
    ن
    1.17
    ก่อน
    1.16
    ก
    1.16
    ado
    1.11
    ents
    1.09
    POSITIVE LOGITS
    ۔
    1.47
    ка
    1.31
    ።
    1.27
    는
    1.23
    は
    1.11
    ು
    1.06
    ﮐ
    1.00
     technically
    0.99
    ᱾
    0.99
    AN
    0.98
    Activations Density 0.000%

    No Known Activations