© 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. 179336
    Prev
    Next
    INDEX
    Explanations

    elves

    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
    亀
    0.40
     Hines
    0.37
    Tenn
    0.36
    KAM
    0.36
    ρέπει
    0.35
     cancelButton
    0.35
    Cow
    0.35
    Ele
    0.35
     亀
    0.35
    jt
    0.35
    POSITIVE LOGITS
     Is
    0.39
     trex
    0.38
    isodes
    0.38
     শিক্ষা
    0.38
    λο
    0.38
     ibu
    0.38
     Ivo
    0.37
    理
    0.36
    쎌
    0.36
     শিক্ষ
    0.36
    Activations Density 0.001%

    No Known Activations