© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30581
    Prev
    Next
    INDEX
    Explanations

    ΔU = Q - W

    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_7_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
     to
    0.44
    ang
    0.44
    eng
    0.41
     =
    0.41
    ua
    0.40
    ada
    0.40
     qilish
    0.40
     όταν
    0.39
    è
    0.39
     quando
    0.39
    POSITIVE LOGITS
    "
    0.54
    म
    0.41
    '
    0.41
    i
    0.40
     refinance
    0.39
     externalities
    0.37
    １
    0.36
    You
    0.36
    YLE
    0.35
     mainframe
    0.34
    Activations Density 0.003%

    No Known Activations