© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215292
    Prev
    Next
    INDEX
    Explanations

    closing brackets or parentheses

    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_31_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
    ubei
    0.40
    abl
    0.37
    誼
    0.37
    rzym
    0.36
     Dada
    0.36
    Marina
    0.35
     साम्राज्य
    0.35
    انہ
    0.35
     Fok
    0.35
    rounds
    0.35
    POSITIVE LOGITS
     TESTS
    0.37
     رائ
    0.34
     calcS
    0.34
    ยังมี
    0.33
     trae
    0.33
     '">'
    0.32
     പിന്തു
    0.32
     terror
    0.32
    терна
    0.32
    ]}/${
    0.32
    Activations Density 0.000%

    No Known Activations