© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32851
    Prev
    Next
    INDEX
    Explanations

    impact, delivery, practice

    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
    ervlak
    0.39
    得以
    0.38
    ørt
    0.37
     Ars
    0.37
     അതു
    0.37
     revela
    0.36
     ก
    0.36
    𐰇
    0.36
    ோது
    0.35
    влека
    0.35
    POSITIVE LOGITS
    SAFER
    0.42
     Siberia
    0.42
     sarcom
    0.40
    SearchParams
    0.40
    მას
    0.40
     SII
    0.39
     Sá
    0.39
     pinion
    0.39
     Connie
    0.38
     Crimea
    0.38
    Activations Density 0.000%

    No Known Activations