© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124474
    Prev
    Next
    INDEX
    Explanations

    Alan (name)

    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
    Δ
    0.67
    ្ឋ
    0.65
    Lens
    0.64
    drink
    0.64
    Пі
    0.64
    Pl
    0.63
     جگہ
    0.63
    P
    0.62
    ght
    0.62
    φαν
    0.62
    POSITIVE LOGITS
    ิน
    0.65
    ي
    0.65
     {
    0.62
    י
    0.61
    ed
    0.60
    ри
    0.59
    ır
    0.58
    нти
    0.57
     carénés
    0.57
    '
    0.56
    Activations Density 0.000%

    No Known Activations