© 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. 131764
    Prev
    Next
    INDEX
    Explanations

    diverse groups and skillsets

    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
    "
    1.29
    $
    1.15
     as
    1.02
    in
    1.01
     it
    0.96
    {
    0.89
     out
    0.85
     we
    0.84
     of
    0.83
    "。
    0.82
    POSITIVE LOGITS
    ты
    1.09
    ту
    1.09
    ле
    1.03
    り
    1.03
    ки
    1.01
    тор
    1.01
    0
    1.01
    ло
    1.00
    Kako
    0.99
    ین
    0.98
    Activations Density 0.003%

    No Known Activations