© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89143
    Prev
    Next
    INDEX
    Explanations

    counterpoint

    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
     julio
    0.71
     pentru
    0.68
     untuk
    0.67
     \
    0.64
    Flavor
    0.63
     menyiapkan
    0.63
    ente
    0.62
     bien
    0.61
     savior
    0.61
    \
    0.61
    POSITIVE LOGITS
    هُ
    0.67
    nú
    0.60
     сама
    0.59
    rés
    0.58
    t
    0.57
     эмо
    0.55
     каждое
    0.55
     важно
    0.55
    уда
    0.54
    єю
    0.53
    Activations Density 0.001%

    No Known Activations