© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50648
    Prev
    Next
    INDEX
    Explanations

    say "("

    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_55_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
    Са
    0.38
     पड़ा
    0.37
    \$
    0.37
    越
    0.36
    启动
    0.35
     guill
    0.35
    整形
    0.35
     pedidos
    0.34
    splitLength
    0.34
     Request
    0.34
    POSITIVE LOGITS
     '),
    0.46
     '(
    0.42
    стное
    0.39
    wanie
    0.39
    !(
    0.38
     khas
    0.38
    inher
    0.38
     }}$,
    0.38
     ).
    0.37
     characteristic
    0.37
    Activations Density 0.001%

    No Known Activations