© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89694
    Prev
    Next
    INDEX
    Explanations

    stack operations like dup

    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_23_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
     "-",
    0.42
    |+\
    0.41
    ๙
    0.40
    +,
    0.40
    opedic
    0.39
     niezbęd
    0.39
    ificent
    0.39
     ?,
    0.38
     อ่าน
    0.37
     Optionally
    0.37
    POSITIVE LOGITS
     ciertos
    0.40
    訓練
    0.40
     Slovenia
    0.39
     calific
    0.39
    칠
    0.39
    വിന്റെ
    0.38
     ta
    0.38
    斻
    0.38
     направления
    0.38
    ላት
    0.37
    Activations Density 0.000%

    No Known Activations