© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230252
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    u
    2.11
    in
    1.88
    as
    1.50
    at
    1.45
    i
    1.36
    n
    1.22
    to
    1.20
    o
    1.20
    inni
    1.08
    ו
    1.07
    POSITIVE LOGITS
    ъ
    1.12
     Abgerufen
    1.05
     Затем
    1.04
     مؤرشف
    1.00
     ancak
    1.00
     zahlreiche
    0.99
     Inoltre
    0.97
     befindet
    0.95
     Ausnahme
    0.93
    ы
    0.93
    Activations Density 0.000%

    No Known Activations