© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245396
    Prev
    Next
    INDEX
    Explanations

    gross margin

    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_40_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
     partner
    0.43
     Islander
    0.39
     An
    0.38
    俦
    0.38
     Clemens
    0.36
    عا
    0.36
     Сла
    0.36
     Env
    0.36
     Weak
    0.35
     Z
    0.35
    POSITIVE LOGITS
     margins
    2.03
     margin
    1.96
    margins
    1.80
    Margin
    1.77
    Margins
    1.73
    margin
    1.72
     marg
    1.70
     Margin
    1.67
     margine
    1.67
     margen
    1.59
    Activations Density 0.002%

    No Known Activations