© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195344
    Prev
    Next
    INDEX
    Explanations

    say "b"

    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_50_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
    Harris
    0.49
    Sleep
    0.43
    Iris
    0.41
    藤
    0.40
    Sleeping
    0.38
    örter
    0.38
     პ
    0.38
    นอน
    0.38
     sleeping
    0.37
    transforms
    0.37
    POSITIVE LOGITS
     tok
    0.43
     spod
    0.43
     marav
    0.41
     escudo
    0.41
     mutants
    0.39
     bonito
    0.39
     toki
    0.38
     الل
    0.38
     L
    0.38
     opera
    0.37
    Activations Density 0.000%

    No Known Activations