© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179873
    Prev
    Next
    INDEX
    Explanations

    government department names

    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_24_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
     C
    0.30
     NE
    0.28
     Ess
    0.27
    core
    0.27
    ƌ
    0.25
    %
    0.25
     And
    0.24
     Queensland
    0.24
     Pelicans
    0.24
    come
    0.24
    POSITIVE LOGITS
    Discrete
    0.29
    ទទ
    0.26
    ographiques
    0.26
    மாண
    0.26
    executionContext
    0.24
    IOException
    0.24
     مہارت
    0.24
    閬
    0.24
    InOut
    0.24
    どのような
    0.24
    Activations Density 0.001%

    No Known Activations