© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43151
    Prev
    Next
    INDEX
    Explanations

    theylive, theia, their breast, thyself, trevor, thevenin

    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_3_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
    '
    1.40
     at
    1.15
    ’
    1.15
     be
    0.86
    р
    0.80
    ER
    0.80
     for
    0.79
    oc
    0.79
    ot
    0.78
     and
    0.77
    POSITIVE LOGITS
    か
    0.71
    গিত
    0.68
    できる
    0.66
    其他
    0.66
    とおり
    0.66
    ール
    0.65
    も
    0.65
     Diario
    0.65
    人
    0.65
     JPL
    0.64
    Activations Density 0.010%

    No Known Activations