© 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. 57050
    Prev
    Next
    INDEX
    Explanations

    handle situations and functions

    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
    for
    0.72
    AW
    0.68
    AI
    0.66
    leding
    0.66
    kyat
    0.66
    t
    0.66
    ARA
    0.65
    AF
    0.63
    AR
    0.63
    yanka
    0.63
    POSITIVE LOGITS
    是
    0.78
    च्या
    0.70
    は
    0.70
     superlative
    0.67
     transcribe
    0.65
     serviço
    0.65
     réalise
    0.65
    星
    0.64
     véritable
    0.60
    源
    0.58
    Activations Density 0.007%

    No Known Activations