© 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. 139452
    Prev
    Next
    INDEX
    Explanations

    plasma or hydrogen formation

    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
     rounds
    0.69
     Rounds
    0.64
    rounds
    0.60
     seventh
    0.57
    Round
    0.56
     ROUND
    0.52
     圆
    0.52
     sixth
    0.51
    ラウンド
    0.51
    Seventh
    0.51
    POSITIVE LOGITS
    宗
    0.40
     NOK
    0.40
     Jong
    0.39
    覃
    0.39
     Lili
    0.37
    地域の
    0.37
     Jon
    0.37
     Blur
    0.36
     Confirm
    0.36
     Jonah
    0.36
    Activations Density 0.000%

    No Known Activations