© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92934
    Prev
    Next
    INDEX
    Explanations

    openai

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    ,
    0.70
    –
    0.52
    )–
    0.48
    table
    0.47
    ,}
    0.46
     =
    0.46
    ,)
    0.45
    .–
    0.44
     $=
    0.44
    market
    0.43
    POSITIVE LOGITS
    _
    0.50
     f
    0.46
    ฟ
    0.40
     ابنائي
    0.40
    蒺
    0.40
     uczniów
    0.39
     ف
    0.39
     trabajadores
    0.38
     کودکان
    0.38
    𝗳
    0.38
    Activations Density 0.002%

    No Known Activations