© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29456
    Prev
    Next
    INDEX
    Explanations

    model

    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_40_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
     Noting
    0.46
     noting
    0.43
     osserv
    0.42
     observe
    0.40
     observed
    0.39
    埶
    0.39
     Observing
    0.38
     resalt
    0.38
     ren
    0.38
    󠁳
    0.38
    POSITIVE LOGITS
     Đ
    0.43
     Bài
    0.40
     Phạm
    0.39
     Vietnam
    0.39
     Process
    0.38
     V
    0.38
     càng
    0.38
    Vietnam
    0.38
     потенциа
    0.37
     anionic
    0.37
    Activations Density 0.001%

    No Known Activations