© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102641
    Prev
    Next
    INDEX
    Explanations

    Brainstorm ideas

    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_16_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
    captive
    0.51
    trunk
    0.51
     نیٹ
    0.48
    溯
    0.48
     Disposition
    0.47
    ántico
    0.47
     eastward
    0.47
    维度
    0.46
     प्रयोग
    0.46
     கட்சி
    0.46
    POSITIVE LOGITS
    AML
    0.61
    LT
    0.60
     september
    0.59
    NSA
    0.57
    OP
    0.55
    MED
    0.55
    8
    0.54
    &
    0.53
    एप
    0.52
    Pr
    0.52
    Activations Density 0.003%

    No Known Activations