© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205158
    Prev
    Next
    INDEX
    Explanations

    images

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     /
    0.49
     sporting
    0.43
    Sport
    0.41
    sport
    0.41
     though
    0.40
     c
    0.39
     consoles
    0.38
     sport
    0.37
     /{
    0.37
     /\
    0.37
    POSITIVE LOGITS
     Plays
    0.48
     Sets
    0.44
     genoemd
    0.42
     sets
    0.41
     Suggestions
    0.41
    Named
    0.41
    named
    0.40
     FEATURES
    0.40
     之
    0.39
     filter
    0.39
    Activations Density 0.003%

    No Known Activations