© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160132
    Prev
    Next
    INDEX
    Explanations

    suds, soap

    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_2_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
    ’
    1.23
    d
    1.14
     of
    1.02
    k
    1.01
    ยัง
    0.93
     I
    0.91
    ll
    0.91
    s
    0.91
    dale
    0.88
    ters
    0.84
    POSITIVE LOGITS
    ро
    1.20
    and
    1.19
    ো
    1.12
    {
    1.09
    л
    1.06
    ב
    1.06
    ل
    1.04
     ？
    1.02
    ал
    0.95
    含ま
    0.94
    Activations Density 0.000%

    No Known Activations