© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14516
    Prev
    Next
    INDEX
    Explanations

    subjective or tricky definitions

    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_40_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
    惋
    0.41
     gotta
    0.40
     سائ
    0.39
    枟
    0.38
     ژوند
    0.38
    迈
    0.37
    usting
    0.35
    ಾ
    0.34
    formas
    0.33
    gast
    0.33
    POSITIVE LOGITS
     definition
    0.67
     Definition
    0.64
     definición
    0.63
    Definition
    0.61
     definitions
    0.61
     definição
    0.60
     Definitions
    0.60
     définition
    0.60
    definition
    0.58
     Defined
    0.55
    Activations Density 0.061%

    No Known Activations