© 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. 35335
    Prev
    Next
    INDEX
    Explanations

    sale" or "val" followed by ending punctuation

    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
    ل
    0.78
    l
    0.74
    ך
    0.74
    も
    0.73
     D
    0.72
     régional
    0.71
     вершин
    0.71
     sayıda
    0.71
    ৩
    0.70
     H
    0.70
    POSITIVE LOGITS
    ing
    1.21
    o
    1.05
     as
    0.89
     are
    0.89
    oys
    0.87
    och
    0.86
    า
    0.82
    a
    0.82
    en
    0.80
    ten
    0.80
    Activations Density 0.012%

    No Known Activations