© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120948
    Prev
    Next
    INDEX
    Explanations

    Learning resources and courses

    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_27_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
    ніх
    0.39
     recouvert
    0.38
    鍍
    0.38
    reproductive
    0.37
    Glass
    0.36
    nucleon
    0.36
    ্কৃতিক
    0.36
    ﾔ
    0.36
    Tissue
    0.35
    enseignement
    0.35
    POSITIVE LOGITS
     quiz
    0.49
     Quiz
    0.48
    quiz
    0.46
     trivia
    0.46
     Miami
    0.45
     ESPN
    0.41
     Trivia
    0.41
     perjud
    0.40
     Direction
    0.40
    题目
    0.39
    Activations Density 0.000%

    No Known Activations