© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220593
    Prev
    Next
    INDEX
    Explanations

    tax, costs, or regulations

    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_31_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
    ˳
    0.45
    گم
    0.42
    ainment
    0.39
    প্রিল
    0.38
     psychologically
    0.36
    Ⅷ
    0.36
     तलैया
    0.35
     undead
    0.35
     Deci
    0.35
     معكم
    0.35
    POSITIVE LOGITS
    ้า
    0.40
    UG
    0.38
     boyhood
    0.37
     বিতর্ক
    0.37
     wafer
    0.37
     aasta
    0.36
     Posterior
    0.36
    ζε
    0.36
    бой
    0.35
     논
    0.35
    Activations Density 0.006%

    No Known Activations