© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58664
    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_59_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
     crash
    0.44
     C
    0.43
    дель
    0.42
     CIV
    0.42
     ダンロップ
    0.41
     CII
    0.39
    ছে
    0.39
     DE
    0.39
     decimals
    0.38
     Drey
    0.38
    POSITIVE LOGITS
     B
    0.59
     บ
    0.55
     ਬ
    0.54
     બ
    0.53
     b
    0.53
     ბ
    0.52
     ဘ
    0.51
     ब
    0.50
     ബ
    0.50
     బ
    0.50
    Activations Density 0.007%

    No Known Activations