© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260691
    Prev
    Next
    INDEX
    Explanations

    hesitation words "uh" or "um"

    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_22_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
     ac
    0.41
    Jordan
    0.41
     Jordan
    0.41
     multipl
    0.40
    R
    0.40
    용
    0.40
     susp
    0.40
    5
    0.40
    L
    0.39
    d
    0.39
    POSITIVE LOGITS
    詑
    0.49
     ",")
    0.45
    IsResolver
    0.44
    జె
    0.43
     ಕೊಡ
    0.43
    籾
    0.43
    MemberList
    0.42
     необходимость
    0.42
    piej
    0.41
     Список
    0.41
    Activations Density 0.000%

    No Known Activations