© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139674
    Prev
    Next
    INDEX
    Explanations

    cautious advice

    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_12_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
     adhipp
    0.62
    <0x81>
    0.54
    నర్
    0.54
    的外
    0.52
     corred
    0.51
    <0x89>
    0.50
    스가
    0.50
    <0xB8>
    0.49
     undeni
    0.49
    <0x82>
    0.49
    POSITIVE LOGITS
    k
    0.70
     kekuatan
    0.64
     nilai
    0.61
    kuat
    0.60
    took
    0.59
     improve
    0.58
     Fear
    0.57
     Plots
    0.57
    賺
    0.56
     gunakan
    0.55
    Activations Density 0.002%

    No Known Activations