© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13180
    Prev
    Next
    INDEX
    Explanations

    aced Repetition

    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_13_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
    氵
    0.22
     It
    0.21
     waters
    0.21
    imoto
    0.21
     we
    0.21
    ht
    0.20
     waterline
    0.20
    水
    0.20
    ◡
    0.20
     We
    0.20
    POSITIVE LOGITS
    Naissance
    0.22
    राबाद
    0.21
    ग्रेड
    0.21
    бир
    0.20
    гія
    0.20
     rechaz
    0.20
    orderby
    0.20
    getFullYear
    0.20
     лигасы
    0.20
    فيذ
    0.20
    Activations Density 0.009%

    No Known Activations