© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 92085
    Prev
    Next
    INDEX
    Explanations

    explaining the name

    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_11_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
    of
    0.24
     ذلك
    0.23
    ரின்
    0.23
    Boxes
    0.21
    viä
    0.21
    <unused296>
    0.21
     Boxes
    0.20
     ubicada
    0.20
    दूस
    0.20
    ذلك
    0.20
    POSITIVE LOGITS
    ;
    0.25
    '
    0.20
    ↵↵
    0.20
    ыл
    0.20
    ottom
    0.20
    ஓ
    0.19
     sporting
    0.19
    eries
    0.18
     Dolphins
    0.18
     sports
    0.18
    Activations Density 0.032%

    No Known Activations