© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129567
    Prev
    Next
    INDEX
    Explanations

    doubt and uncertainty

    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_6_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
    )}.
    0.82
    くちゃ
    0.79
    )].
    0.77
    '
    0.75
     서비스를
    0.74
     дости
    0.73
     감사
    0.73
    {
    0.73
    お金
    0.72
    IService
    0.71
    POSITIVE LOGITS
    in
    1.64
    ка
    1.59
    ك
    1.51
    na
    1.47
    k
    1.45
    p
    1.41
    l
    1.40
    i
    1.38
    nın
    1.33
    lardan
    1.32
    Activations Density 0.000%

    No Known Activations