© 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. 221047
    Prev
    Next
    INDEX
    Explanations

    find it + adjective

    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
    ف
    0.61
    علم
    0.54
    c
    0.53
    k
    0.53
    హ
    0.53
    n
    0.49
    ا
    0.49
    إ
    0.48
    ഇ
    0.47
    ك
    0.47
    POSITIVE LOGITS
     farce
    0.40
    licting
    0.39
    ulates
    0.38
    startsWith
    0.38
    ells
    0.37
     pyrolysis
    0.37
    rights
    0.37
    ples
    0.37
    ড়িত
    0.37
     ’’
    0.37
    Activations Density 0.005%

    No Known Activations