© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100410
    Prev
    Next
    INDEX
    Explanations

    O

    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_16_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
     খ্র
    0.59
    ებისა
    0.57
    Wood
    0.56
    Organic
    0.55
     -$
    0.55
    olids
    0.54
    Ed
    0.53
    اتها
    0.52
    竑
    0.52
    ěla
    0.51
    POSITIVE LOGITS
     lake
    0.58
     water
    0.58
     nước
    0.56
    cek
    0.53
     glacial
    0.50
     drifting
    0.50
     saltwater
    0.50
     sonde
    0.50
    滄
    0.49
     डूब
    0.49
    Activations Density 0.003%

    No Known Activations