© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80596
    Prev
    Next
    INDEX
    Explanations

    National

    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_53_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
    ermark
    0.39
     scrubber
    0.38
     tubercle
    0.38
     Garten
    0.36
    ശ
    0.35
     database
    0.35
     Hermitian
    0.35
     Сара
    0.35
     Kamane
    0.35
     multiplicative
    0.35
    POSITIVE LOGITS
     რ
    0.38
    ADIAN
    0.37
    秶
    0.36
    迟
    0.36
    Bur
    0.36
    Ｎ
    0.36
     radians
    0.36
    NG
    0.35
    Ν
    0.35
    क़
    0.35
    Activations Density 0.004%

    No Known Activations