© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14895
    Prev
    Next
    INDEX
    Explanations

    or, comma, parenthesis structures

    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_15_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
    燬
    0.11
     हू
    0.11
    地位
    0.11
    <unused47>
    0.11
     충분
    0.11
     మి
    0.10
    特典
    0.10
     dajj
    0.10
    kBtu
    0.10
     그의
    0.10
    POSITIVE LOGITS
    er
    0.14
    or
    0.14
    ik
    0.13
    ie
    0.13
    ose
    0.13
    in
    0.13
    en
    0.12
    e
    0.12
    id
    0.12
    ate
    0.12
    Activations Density 0.263%

    No Known Activations