© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207100
    Prev
    Next
    INDEX
    Explanations

    start actions

    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_20_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
     vertexList
    0.26
     epistem
    0.25
     defendants
    0.25
    アイデア
    0.25
     historically
    0.23
    đen
    0.23
     succès
    0.23
    𝙵
    0.23
     Zhi
    0.23
    probabilities
    0.23
    POSITIVE LOGITS
     হওয়া
    0.27
    اب
    0.27
    并不是
    0.26
    과의
    0.25
    战争
    0.25
    ザ
    0.24
     відповідно
    0.24
    ಜ
    0.24
    মানব
    0.24
    ovin
    0.23
    Activations Density 0.008%

    No Known Activations