© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159290
    Prev
    Next
    INDEX
    Explanations

    **Text: **

    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_2_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
    d
    1.46
    of
    1.16
    a
    1.15
    and
    1.11
    on
    1.00
    use
    0.99
    o
    0.98
    𝘥
    0.95
    га
    0.93
    dan
    0.92
    POSITIVE LOGITS
    ના
    1.30
    (
    1.24
    কে
    1.16
    Ｅ
    1.04
    ها
    1.03
    ні
    1.02
    ру
    1.00
    <0x0D>
    0.98
    UT
    0.95
    ↵
    0.93
    Activations Density 0.008%

    No Known Activations