© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165575
    Prev
    Next
    INDEX
    Explanations

    with you

    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_31_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
    遵循
    0.36
     whats
    0.35
     saludable
    0.34
     জাহাজ
    0.34
    ská
    0.33
     entusiasmo
    0.33
     intereses
    0.32
    优
    0.32
     adherence
    0.31
     tils
    0.31
    POSITIVE LOGITS
    inig
    0.38
     him
    0.37
     нам
    0.35
     lui
    0.35
    werks
    0.34
     постоянно
    0.34
    inck
    0.34
     Gell
    0.34
     them
    0.33
     Olsen
    0.33
    Activations Density 0.000%

    No Known Activations