© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16496
    Prev
    Next
    INDEX
    Explanations

    unexpected but

    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
    𒌋
    0.40
    속
    0.38
     Purchased
    0.38
    ="*"
    0.35
     ngũ
    0.35
     vrije
    0.35
     relent
    0.35
     펼
    0.34
     구입
    0.33
     portfolio
    0.33
    POSITIVE LOGITS
     unexpectedly
    0.50
     неожидан
    0.50
     überras
    0.49
     unexpected
    0.49
    unexpected
    0.46
    吓
    0.40
     ipc
    0.40
     Unexpected
    0.40
     surprised
    0.39
     inesper
    0.39
    Activations Density 0.032%

    No Known Activations