© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42022
    Prev
    Next
    INDEX
    Explanations

    certain word endings / suffixes

    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
    li
    0.77
    t
    0.74
    т
    0.69
    a
    0.64
    de
    0.63
    liz
    0.62
    গুরু
    0.59
    汅
    0.59
    y
    0.59
    et
    0.58
    POSITIVE LOGITS
    begin
    0.61
     transcoding
    0.57
    お知らせ
    0.57
    Couldn
    0.55
     stimuli
    0.52
     erkennt
    0.52
     مارس
    0.51
     soweit
    0.51
    書館
    0.51
     synthes
    0.50
    Activations Density 0.011%

    No Known Activations