© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139582
    Prev
    Next
    INDEX
    Explanations

    flavor of the week / tidbits

    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_12_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
    зах
    0.54
     méth
    0.50
    ᓲ
    0.48
    еты
    0.47
     baddies
    0.47
    า
    0.47
     والصلاه
    0.46
    зия
    0.46
    для
    0.46
    нави
    0.46
    POSITIVE LOGITS
     Parkinson
    0.46
    o
    0.44
     Anfang
    0.43
     Хоро
    0.42
    la
    0.42
     El
    0.41
     Abd
    0.40
     Аб
    0.40
     Abre
    0.40
     ഇ
    0.40
    Activations Density 0.000%

    No Known Activations