© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1871
    Prev
    Next
    INDEX
    Explanations

    legal

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    ಡು
    0.37
     খে
    0.35
     bracing
    0.35
     amputation
    0.35
     смер
    0.35
    ӥ
    0.34
     বাহুল্য
    0.34
    ଷ୍
    0.34
     luminal
    0.34
    愀
    0.34
    POSITIVE LOGITS
     legal
    2.77
    Legal
    2.67
    legal
    2.58
     Legal
    2.53
     LEGAL
    2.31
     कानूनी
    2.22
     legales
    2.22
     legais
    2.11
     юриди
    2.08
     legale
    2.08
    Activations Density 0.102%

    No Known Activations