© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87398
    Prev
    Next
    INDEX
    Explanations

    run after

    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_3_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
    were
    0.70
    ola
    0.69
    illos
    0.68
    ＂
    0.66
    ria
    0.66
    stek
    0.65
    veh
    0.64
    viso
    0.63
    beda
    0.63
    etzes
    0.63
    POSITIVE LOGITS
    ك
    1.05
    י
    1.01
    ↵
    0.95
    ,
    0.86
     jeopardize
    0.84
     hasten
    0.82
     indicate
    0.80
     jeopard
    0.80
    יות
    0.80
     liquidate
    0.79
    Activations Density 0.002%

    No Known Activations