© 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. 89189
    Prev
    Next
    INDEX
    Explanations

    playoff rounds and series

    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
     caro
    0.54
     ;
    0.54
    ei
    0.50
     à
    0.50
    ၂
    0.49
    ｅ
    0.48
    }=
    0.48
    car
    0.48
    fda
    0.48
     :
    0.48
    POSITIVE LOGITS
     гаранти
    0.55
     функция
    0.55
     zašt
    0.54
     значение
    0.54
     анализ
    0.53
     KON
    0.50
     relevancia
    0.50
     değer
    0.50
     konzerv
    0.49
     predator
    0.49
    Activations Density 0.008%

    No Known Activations