© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89719
    Prev
    Next
    INDEX
    Explanations

    avg

    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_11_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
    -
    0.23
    会の
    0.21
    ase
    0.20
    chett
    0.18
     dice
    0.18
     certo
    0.18
              
    0.18
    neath
    0.18
     deix
    0.18
    uate
    0.18
    POSITIVE LOGITS
    ４
    0.19
    タイプ
    0.19
    otricha
    0.19
    ル
    0.19
     américain
    0.18
    钏
    0.18
    PHP
    0.18
    د
    0.18
    ルフ
    0.18
     ૩
    0.18
    Activations Density 0.001%

    No Known Activations