© 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. 124214
    Prev
    Next
    INDEX
    Explanations

    ways

    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
    分けて
    0.69
    ᱭ
    0.69
     stimulate
    0.68
    ﻟ
    0.68
    of
    0.66
    মতি
    0.66
    ဆောင်
    0.64
    ຈັດສົ່ງ
    0.62
    鹑
    0.62
     membres
    0.61
    POSITIVE LOGITS
    k
    0.65
    ene
    0.64
    rl
    0.64
    ru
    0.62
    ears
    0.61
    ط
    0.60
    antes
    0.59
    غ
    0.59
     in
    0.58
    <0x9E>
    0.57
    Activations Density 0.000%

    No Known Activations