© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89485
    Prev
    Next
    INDEX
    Explanations

    chlorides, compounds, acyl halides

    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_3_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
     merchants
    0.71
     Merchants
    0.70
     불구하고
    0.67
     prestar
    0.66
    ({\
    0.64
     saludar
    0.64
    ari
    0.63
     solicitar
    0.63
     estimular
    0.63
    iril
    0.61
    POSITIVE LOGITS
    та
    1.11
    า
    0.86
    ק
    0.81
     was
    0.79
    0.72
    was
    0.72
    ما
    0.71
    gruppen
    0.69
    в
    0.69
    ها
    0.68
    Activations Density 0.000%

    No Known Activations