© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246410
    Prev
    Next
    INDEX
    Explanations

    registry URLs

    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_40_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
    Comput
    0.38
    ongan
    0.37
    flav
    0.36
    甩
    0.36
    记录
    0.35
    Sonic
    0.35
     Comput
    0.35
    rownames
    0.35
    型
    0.34
    형
    0.34
    POSITIVE LOGITS
     TMC
    0.46
     sneezing
    0.45
     Tanz
    0.39
    ésie
    0.39
     artisans
    0.38
     AMC
    0.38
     TDC
    0.38
     correg
    0.38
     artes
    0.38
     далее
    0.38
    Activations Density 0.000%

    No Known Activations