© 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. 229638
    Prev
    Next
    INDEX
    Explanations

    mongo import

    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
    ad
    1.85
    ar
    1.53
    c
    1.37
    ot
    1.24
    as
    1.21
    ol
    1.21
    in
    1.20
    ق
    1.20
    cx
    1.20
    en
    1.18
    POSITIVE LOGITS
    ئے
    0.87
    イ
    0.82
    '
    0.81
    йи
    0.80
     impuestos
    0.79
    ба
    0.79
    లు
    0.79
    يا
    0.78
    ยนต์
    0.78
    ي
    0.78
    Activations Density 0.000%

    No Known Activations