© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101538
    Prev
    Next
    INDEX
    Explanations

    hotel suite

    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_14_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
    type
    0.48
    Phase
    0.48
    T
    0.47
    tos
    0.47
    ව
    0.46
     =
    0.46
    P
    0.46
    Name
    0.45
    Vý
    0.45
    h
    0.44
    POSITIVE LOGITS
     mandi
    0.54
     cambiamenti
    0.53
     quantidades
    0.52
     carinatis
    0.50
     количества
    0.50
     eszköz
    0.50
    ôn
    0.48
     ativos
    0.48
     cambios
    0.48
     atomizer
    0.48
    Activations Density 0.000%

    No Known Activations