© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133815
    Prev
    Next
    INDEX
    Explanations

    tax reporting

    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_1_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
    o
    1.61
    ed
    1.35
    .
    1.35
    ov
    1.30
    es
    1.18
    ing
    1.09
    os
    1.09
     mache
    0.98
    aire
    0.98
    ee
    0.96
    POSITIVE LOGITS
    ні
    1.49
    ну
    1.06
    را
    1.06
    τών
    1.06
    ση
    1.04
    that
    1.02
    。
    1.02
    reactant
    1.00
    னின்
    0.96
    ຖານ
    0.95
    Activations Density 0.003%

    No Known Activations