© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177168
    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_24_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
     эффективность
    0.45
     ripet
    0.42
     энциклопедия
    0.40
     غال
    0.40
     exaggeration
    0.39
    ArchivePath
    0.38
    蓖
    0.38
     ilmiah
    0.38
    モス
    0.38
     مض
    0.37
    POSITIVE LOGITS
     forthwith
    0.48
     transmits
    0.41
     transmit
    0.41
     patched
    0.39
     우
    0.38
     naval
    0.38
    णियों
    0.37
     baffled
    0.37
    ➋
    0.36
     sends
    0.36
    Activations Density 0.000%

    No Known Activations