© 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. 125661
    Prev
    Next
    INDEX
    Explanations

    html content scraping

    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
    an
    0.86
    ay
    0.76
    us
    0.70
    a
    0.70
    seits
    0.69
    Versions
    0.66
    G
    0.65
    obian
    0.64
    seu
    0.64
    ان
    0.64
    POSITIVE LOGITS
    ра
    0.75
     б
    0.67
     mö
    0.63
    ба
    0.62
    ф
    0.62
     neurotrans
    0.61
     फोन
    0.61
    <0x99>
    0.59
    <0xB9>
    0.59
    ч
    0.59
    Activations Density 0.007%

    No Known Activations