© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219300
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    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_47_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
    ంగళ
    0.38
     phosphate
    0.38
    ಿ
    0.38
     জেগে
    0.37
     आरएफ
    0.37
    に使用
    0.36
    授予
    0.36
     문의
    0.36
     consulte
    0.35
     ক্লে
    0.35
    POSITIVE LOGITS
     Davy
    0.36
    tak
    0.36
    Boo
    0.35
     Boo
    0.35
    rices
    0.34
     Schub
    0.34
    𝘞
    0.34
    anske
    0.34
    replay
    0.34
    ска
    0.34
    Activations Density 0.000%

    No Known Activations