© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117769
    Prev
    Next
    INDEX
    Explanations

    UTF-8 characters encoding

    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_27_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
     প্রিন
    0.44
     adversarial
    0.41
     MANUFACTURING
    0.40
     suboptimal
    0.40
     lousy
    0.40
     AVER
    0.40
    RODUCTION
    0.39
    꼰
    0.39
     manufactures
    0.38
    लीस
    0.38
    POSITIVE LOGITS
     même
    0.40
     reflux
    0.38
     sí
    0.38
     einfach
    0.37
     hypers
    0.37
    end
    0.36
     ако
    0.36
    이지만
    0.36
    ends
    0.35
    encrypt
    0.35
    Activations Density 0.001%

    No Known Activations