© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50786
    Prev
    Next
    INDEX
    Explanations

    speak + preposition/object

    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_10_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
    re
    0.44
    是因为
    0.40
    User
    0.40
    لي
    0.40
    Message
    0.40
    서는
    0.40
    は
    0.39
    Session
    0.39
    Generic
    0.38
    Request
    0.38
    POSITIVE LOGITS
     innovating
    0.35
     of
    0.33
     out
    0.32
     thinkers
    0.32
    ۰
    0.32
    hetic
    0.31
     Empor
    0.31
    ляє
    0.30
     появи
    0.30
    plicit
    0.29
    Activations Density 0.010%

    No Known Activations