© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195690
    Prev
    Next
    INDEX
    Explanations

    blessed

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    mo
    0.43
     Indiana
    0.41
     Z
    0.40
    heet
    0.40
    ंडल
    0.38
    vind
    0.38
     Bl
    0.38
     bliz
    0.38
    ind
    0.38
     ছাউ
    0.38
    POSITIVE LOGITS
    ᠰ
    0.38
    辉
    0.37
    喤
    0.37
     Stet
    0.36
    巉
    0.35
     কলের
    0.35
    伴
    0.35
    晌
    0.35
    𝒔
    0.35
     acetylcholine
    0.35
    Activations Density 0.001%

    No Known Activations