© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215677
    Prev
    Next
    INDEX
    Explanations

    AW

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     thous
    0.40
     आख
    0.40
    owicz
    0.38
     chees
    0.38
    閣
    0.38
     поч
    0.38
    ческие
    0.36
    廻
    0.36
     Mous
    0.35
     หัด
    0.35
    POSITIVE LOGITS
    AS
    0.43
    ledger
    0.41
     clergy
    0.39
     suffit
    0.39
     kendaraan
    0.39
     المد
    0.38
     Cargo
    0.38
     vozila
    0.38
    PT
    0.37
    클
    0.36
    Activations Density 0.010%

    No Known Activations