© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45833
    Prev
    Next
    INDEX
    Explanations

    see how, what, if

    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_10_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
     uang
    0.57
    ਾ
    0.52
     ataupun
    0.49
    ל
    0.46
     sarà
    0.44
    국의
    0.44
    '
    0.43
     connaît
    0.42
     resusc
    0.42
     auxquelles
    0.42
    POSITIVE LOGITS
    rt
    0.54
    ة
    0.51
    ij
    0.47
    life
    0.47
    st
    0.47
    lane
    0.46
    ict
    0.45
    _
    0.45
    ice
    0.44
    ijama
    0.44
    Activations Density 0.024%

    No Known Activations