© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97058
    Prev
    Next
    INDEX
    Explanations

    level of effort

    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_14_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
    重建
    0.21
    エリ
    0.21
     IHDA
    0.21
    ﺍ
    0.20
    ແມ
    0.19
    ají
    0.19
    擢
    0.18
     соеди
    0.18
    ạm
    0.18
     מס
    0.18
    POSITIVE LOGITS
    q
    0.23
    o
    0.22
    u
    0.21
    varlak
    0.19
    otta
    0.19
     essentials
    0.19
    :",
    0.18
    teilung
    0.18
    io
    0.18
    PARTMENT
    0.18
    Activations Density 0.014%

    No Known Activations