© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143186
    Prev
    Next
    INDEX
    Explanations

    ǒ and UIKit

    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_0_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
    s
    1.60
    1.53
    ä
    1.37
    d
    1.25
     Tradition
    1.20
     över
    1.17
    e
    1.17
    ר
    1.16
    dür
    1.16
    ల
    1.16
    POSITIVE LOGITS
    ła
    1.67
    та
    1.66
    ᱐
    1.56
    なる
    1.36
    した
    1.34
    ᱙
    1.31
    ۰
    1.30
    𝟎
    1.27
    써
    1.26
    ρα
    1.23
    Activations Density 0.001%

    No Known Activations