© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 29887
    Prev
    Next
    INDEX
    Explanations

    for followed by purpose

    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_7_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    L
    0.43
    D
    0.39
    O
    0.38
    M
    0.37
     In
    0.37
    K
    0.36
    F
    0.36
    In
    0.35
    S
    0.34
     It
    0.34
    POSITIVE LOGITS
    ри
    0.42
    n
    0.41
    сто
    0.37
     graphon
    0.36
    ва
    0.35
    ת
    0.34
    лся
    0.32
    त
    0.32
    ש
    0.32
    larda
    0.32
    Activations Density 0.091%

    No Known Activations