© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164303
    Prev
    Next
    INDEX
    Explanations

    hay, มี, muchos, cantidad

    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_13_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
     administers
    0.58
     {}
    0.51
     is
    0.50
     मौजूदा
    0.49
    }/>
    0.49
    Loksatta
    0.49
    ier
    0.49
    ↵↵↵↵↵↵↵↵↵↵
    0.48
     সেটা
    0.48
    ↵↵↵
    0.47
    POSITIVE LOGITS
     véhicule
    0.59
     vehículo
    0.57
    ໄດ້
    0.55
     vehículos
    0.54
     Wagon
    0.54
     грузо
    0.53
    țiile
    0.52
     véhicules
    0.52
    quantidade
    0.52
     površ
    0.50
    Activations Density 0.003%

    No Known Activations