© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45881
    Prev
    Next
    INDEX
    Explanations

    claim construction and drafting

    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_13_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
    <
    0.62
    s
    0.58
    t
    0.50
     orthogon
    0.48
    <0x83>
    0.46
     dictated
    0.46
     scorers
    0.46
    ंथ
    0.45
     चूंकि
    0.45
    三
    0.45
    POSITIVE LOGITS
    Pv
    0.54
    ckså
    0.54
     Và
    0.52
     &,
    0.52
    ור
    0.52
     BorderRadius
    0.52
     nové
    0.52
     ஆண்
    0.52
    ָ
    0.52
    imismo
    0.51
    Activations Density 0.001%

    No Known Activations