© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121869
    Prev
    Next
    INDEX
    Explanations

    code keywords `int`, `CONF`, `Write`, `Command`

    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_37_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
     Partly
    0.41
    増や
    0.40
     конвер
    0.38
     partly
    0.38
    <unused91>
    0.37
     dt
    0.37
     சோதனை
    0.37
    ምት
    0.36
    <unused80>
    0.35
    मील
    0.35
    POSITIVE LOGITS
     guaranteed
    0.40
     guarante
    0.39
     Guaranteed
    0.38
     baby
    0.37
     Laksh
    0.37
     guarantee
    0.36
     lak
    0.36
    Ń
    0.36
    balances
    0.36
     garantia
    0.36
    Activations Density 0.000%

    No Known Activations