© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 203827
    Prev
    Next
    INDEX
    Explanations

    Anti-Defamation League and Federation

    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
     to
    1.29
    (
    1.20
     by
    1.09
    {
    1.02
    to
    0.83
    UM
    0.81
    。
    0.81
    <
    0.81
    p
    0.76
    OD
    0.74
    POSITIVE LOGITS
    in
    0.95
     ﺍ
    0.86
    ᱽ
    0.86
    arid
    0.84
     Մ
    0.84
    ků
    0.80
    t
    0.80
    ᕝ
    0.80
    en
    0.79
     Бү
    0.79
    Activations Density 0.002%

    No Known Activations