© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107584
    Prev
    Next
    INDEX
    Explanations

    Cython extensions

    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_1_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
     is
    1.72
    1.34
    는
    1.34
     was
    1.31
    是
    1.27
    ри
    1.26
     (
    1.17
     It
    1.15
     of
    1.07
     has
    1.07
    POSITIVE LOGITS
    ພວກເຮ
    1.19
    ल
    1.16
     Londra
    1.12
     olimp
    1.11
    юнча
    1.10
     شرطونه
    1.09
     optimise
    1.07
    excludes
    1.06
     شرطونو
    1.06
     rilas
    1.05
    Activations Density 0.000%

    No Known Activations