© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45380
    Prev
    Next
    INDEX
    Explanations

    arc or circle with parameters

    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_22_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
    的
    0.52
    iação
    0.46
    lação
    0.46
    滑动
    0.45
     白色
    0.42
     algumas
    0.42
     idade
    0.42
    hamento
    0.42
    譬
    0.42
     guarda
    0.41
    POSITIVE LOGITS
     blog
    0.45
     masterpieces
    0.43
     μπορού
    0.43
     zk
    0.43
    ried
    0.42
     blir
    0.42
     masterpiece
    0.41
     clear
    0.41
    agini
    0.40
     world
    0.39
    Activations Density 0.000%

    No Known Activations