© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193481
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
     i
    0.55
    w
    0.53
    ل
    0.51
    v
    0.48
    j
    0.48
    c
    0.47
    alak
    0.47
    idio
    0.46
     _
    0.46
     Anh
    0.46
    POSITIVE LOGITS
     بیټ
    0.49
    。「
    0.45
    ‏‏
    0.44
    를
    0.44
    ילה
    0.43
     reentry
    0.43
     estan
    0.43
     ದೂರ
    0.43
    一项
    0.42
    ایت
    0.42
    Activations Density 0.000%

    No Known Activations