© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26914
    Prev
    Next
    INDEX
    Explanations

    ":" followed by data

    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_10_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
    0.52
    ta
    0.52
    g
    0.51
    tr
    0.51
    d
    0.50
    ten
    0.49
    л
    0.48
    લ
    0.47
    ts
    0.46
    z
    0.46
    POSITIVE LOGITS
    '
    0.57
    。
    0.52
    {
    0.49
    Você
    0.41
    ੯
    0.41
     horizonte
    0.40
     incessantly
    0.39
    埶
    0.39
    ！」
    0.39
     exuber
    0.39
    Activations Density 0.079%

    No Known Activations