© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103440
    Prev
    Next
    INDEX
    Explanations

    windsurfing and similar activities

    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_1_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
    在
    1.41
    س
    1.20
     in
    1.19
    可以
    1.12
    а
    1.07
    人
    1.05
    ра
    1.03
    с
    1.03
    会
    1.02
    的
    1.02
    POSITIVE LOGITS
    :
    1.15
    '
    0.94
    iD
    0.86
    i
    0.86
    ()'
    0.84
     merda
    0.84
     Ples
    0.83
     lParam
    0.83
    iol
    0.82
    isr
    0.82
    Activations Density 0.000%

    No Known Activations