© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200389
    Prev
    Next
    INDEX
    Explanations

    Game of Thrones names and concepts

    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
    }$
    0.49
     राष्ट्र
    0.49
     ආහාර
    0.49
    $,
    0.48
    देश
    0.48
    高校
    0.47
     acaba
    0.47
    $.
    0.47
     kı
    0.46
     bắn
    0.45
    POSITIVE LOGITS
     Planets
    0.50
    AppName
    0.45
    ச்சின்ன
    0.45
    Tempo
    0.45
     memória
    0.45
     PACE
    0.44
    Img
    0.44
     పెద్ద
    0.43
    emaster
    0.43
     Regen
    0.43
    Activations Density 0.001%

    No Known Activations