© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15436
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by "we"

    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_34_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
     frut
    0.42
     dishonesty
    0.40
     insufficiency
    0.39
     lousy
    0.39
     corruption
    0.39
    ῎
    0.38
     aportar
    0.38
     unsound
    0.37
     gosh
    0.37
     Sexton
    0.37
    POSITIVE LOGITS
    )}{(
    0.39
    重新
    0.36
    }{(
    0.35
    眙
    0.35
    Cameras
    0.34
    Renderer
    0.34
    voj
    0.34
    Flash
    0.34
    ગી
    0.34
    umpang
    0.34
    Activations Density 0.043%

    No Known Activations