© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241575
    Prev
    Next
    INDEX
    Explanations

    final seasons, K4, case, Widmore, US, total

    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_25_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
     undivided
    0.20
     $^{
    0.20
     ವೆ
    0.20
    abilities
    0.19
     correlations
    0.19
     correlation
    0.19
     Correlations
    0.19
    ž
    0.18
    web
    0.18
     wholes
    0.18
    POSITIVE LOGITS
    ണ്ടും
    0.25
     सफाया
    0.25
     supaya
    0.24
     restante
    0.23
     serangan
    0.23
    GetService
    0.22
     dalam
    0.22
     desemb
    0.22
     consegu
    0.22
     transferência
    0.22
    Activations Density 0.001%

    No Known Activations