© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17187
    Prev
    Next
    INDEX
    Explanations

    centrifugal pumps and fans

    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_15_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
     이미지
    0.54
    ENTAL
    0.51
     これらの
    0.51
    ۸
    0.51
     アイス
    0.50
    人類
    0.50
    Ice
    0.49
    אן
    0.49
     李
    0.49
     criteri
    0.49
    POSITIVE LOGITS
    prits
    0.48
    unque
    0.47
     Prit
    0.47
    gebung
    0.47
     българ
    0.46
    yszer
    0.46
    好好
    0.46
    ereco
    0.46
     Gul
    0.45
    udiant
    0.44
    Activations Density 0.005%

    No Known Activations