© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134642
    Prev
    Next
    INDEX
    Explanations

    list item marker

    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_6_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
     is
    1.05
     phonons
    1.01
     -
    1.00
    ö
    0.95
     atoms
    0.93
     shards
    0.93
     __
    0.90
     were
    0.89
     (
    0.88
     irritable
    0.88
    POSITIVE LOGITS
    出
    1.01
    ו
    0.90
    н
    0.89
    м
    0.81
    ाइन
    0.79
    ىڭ
    0.74
    assertEqual
    0.73
    nPortIndex
    0.73
    로부터
    0.73
    at
    0.72
    Activations Density 0.001%

    No Known Activations