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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93158
    Prev
    Next
    INDEX
    Explanations

    BBC Radio sources

    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
     buck
    0.47
     foot
    0.46
     construction
    0.46
    uot
    0.46
    弇
    0.45
    ੭
    0.44
     voet
    0.44
    igation
    0.43
    ú
    0.42
     assault
    0.42
    POSITIVE LOGITS
     Германия
    0.59
     Обра
    0.57
    ដែល
    0.56
    ដែលមាន
    0.55
    يمكن
    0.54
    ডেন
    0.54
     Как
    0.53
    ಎ
    0.53
     waarmee
    0.52
    ي
    0.52
    Activations Density 0.006%

    No Known Activations