© 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. 226312
    Prev
    Next
    INDEX
    Explanations

    law firm

    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
    ل
    0.33
    ת
    0.28
    ку
    0.28
    média
    0.27
    ्रीट
    0.25
    కు
    0.25
    راب
    0.24
    nál
    0.24
    dengan
    0.24
     conflic
    0.24
    POSITIVE LOGITS
    {
    0.25
    यर
    0.24
    o
    0.24
    ía
    0.22
    òn
    0.21
     arousal
    0.21
    ;
    0.20
    积极
    0.20
    EEEE
    0.19
     hydrochloride
    0.19
    Activations Density 0.004%

    No Known Activations