© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80404
    Prev
    Next
    INDEX
    Explanations

    product descriptions and names

    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
    ни
    1.56
    4
    1.51
    5
    1.50
    ли
    1.38
    3
    1.29
    2
    1.28
     зависи
    1.20
    каз
    1.16
    ход
    1.16
     કરતા
    1.13
    POSITIVE LOGITS
    त
    1.78
    ם
    1.76
    도
    1.74
    an
    1.68
    ও
    1.63
    k
    1.45
     an
    1.43
    t
    1.41
    ac
    1.38
    q
    1.36
    Activations Density 0.000%

    No Known Activations