© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6706
    Prev
    Next
    INDEX
    Explanations

    fetch POST method

    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_39_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
    㳳
    0.43
    erder
    0.42
    leiter
    0.40
     chac
    0.40
    䢎
    0.39
     oligodendrocyte
    0.39
    決
    0.38
    㶲
    0.38
    路線
    0.37
    下单
    0.37
    POSITIVE LOGITS
     traditional
    0.47
    Traditional
    0.41
    traditional
    0.41
     Traditional
    0.40
     conventional
    0.38
     pale
    0.37
     McCormick
    0.36
    ТУ
    0.35
     мастеров
    0.35
    зах
    0.35
    Activations Density 0.002%

    No Known Activations