© 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. 101463
    Prev
    Next
    INDEX
    Explanations

    insurance, general, poundland, garage, essex

    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
     αποτε
    0.43
     órgãos
    0.39
     οπο
    0.39
     interessa
    0.38
    👮
    0.36
    腧
    0.36
     Muller
    0.36
    াকা
    0.36
     nouvel
    0.36
     Annapolis
    0.35
    POSITIVE LOGITS
     Huddersfield
    0.50
    seven
    0.44
     पढ़ने
    0.42
    라
    0.41
    读
    0.41
    드의
    0.40
    S
    0.39
    d
    0.39
    resnet
    0.39
    राट
    0.39
    Activations Density 0.006%

    No Known Activations