© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152037
    Prev
    Next
    INDEX
    Explanations

    mixed characters and languages

    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_60_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
    <0xA6>
    0.64
    <0xAB>
    0.55
    <0xA8>
    0.54
    <0xA7>
    0.50
    <0xA5>
    0.49
    <0xB8>
    0.45
    <0xA3>
    0.45
     debo
    0.44
    <0xAA>
    0.44
    <0xA4>
    0.43
    POSITIVE LOGITS
     ప్ర
    0.66
    <0x98>
    0.63
     :
    0.61
    <0x93>
    0.59
    <0x99>
    0.57
    <0x95>
    0.57
    <0x9A>
    0.56
    <0x94>
    0.52
    ‌
    0.51
    ‌లో
    0.50
    Activations Density 0.000%

    No Known Activations