© 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. 81002
    Prev
    Next
    INDEX
    Explanations

    Romania

    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
     soy
    0.42
     Ad
    0.40
    osomes
    0.39
     bast
    0.39
     basta
    0.38
     Bă
    0.38
    嫩
    0.38
    ционными
    0.38
     ㄴ
    0.38
     bail
    0.37
    POSITIVE LOGITS
     z
    0.64
     ز
    0.50
    z
    0.50
     Z
    0.47
    Z
    0.47
     o
    0.47
     Zar
    0.45
     з
    0.44
     O
    0.42
     zin
    0.42
    Activations Density 0.000%

    No Known Activations