© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213088
    Prev
    Next
    INDEX
    Explanations

    access / accessibility

    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_5_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
    s
    1.74
    il
    1.60
     of
    1.50
    g
    1.46
    l
    1.40
    い
    1.32
    ை
    1.29
    ри
    1.24
    im
    1.22
    r
    1.21
    POSITIVE LOGITS
    0
    1.52
    ,
    1.08
    {
    1.08
    ૦
    1.08
    ０
    1.06
    ০০
    1.05
    ो
    1.04
    них
    1.00
    $
    0.93
     ollut
    0.89
    Activations Density 0.000%

    No Known Activations