© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220737
    Prev
    Next
    INDEX
    Explanations

    examples of specific terms or concepts

    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_10_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
    na
    0.50
    vaa
    0.46
    6
    0.46
    8
    0.44
    if
    0.43
    ID
    0.43
    1
    0.43
    unn
    0.42
    onta
    0.42
    ft
    0.42
    POSITIVE LOGITS
    𝚋
    0.57
    ériences
    0.50
    𝒈
    0.49
    𝙤
    0.48
    再生
    0.48
     болезни
    0.47
     захворю
    0.47
     overdrive
    0.47
     അതേ
    0.47
    дьми
    0.47
    Activations Density 0.000%

    No Known Activations