© 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
    2. Gemma-3-27B-IT
    3. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 15642
    Prev
    Next
    INDEX
    Explanations

    search results or matches

    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
    ありません
    0.22
    हर
    0.22
    opolitical
    0.21
    <0xAC>
    0.20
    <0xB9>
    0.20
    l
    0.20
    lerdir
    0.20
    ﺣ
    0.20
    ні
    0.20
    नई
    0.20
    POSITIVE LOGITS
     florist
    0.25
     flavon
    0.24
    cevam
    0.24
     처리
    0.23
     сохранить
    0.22
     የበ
    0.22
     benzoate
    0.22
     patina
    0.22
     цветы
    0.22
     小物
    0.22
    Activations Density 0.029%

    No Known Activations