© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48493
    Prev
    Next
    INDEX
    Explanations

    currency

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    phrases related to user input and model responses in a conversational AI context.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    ᡤ
    0.59
     térm
    0.55
     rộng
    0.51
    쐞
    0.51
    無論
    0.50
     fidèle
    0.50
    ル
    0.50
    ⵢ
    0.49
    னோ
    0.49
     विभागों
    0.49
    POSITIVE LOGITS
     Mrs
    0.55
     ¥
    0.50
     Shortly
    0.47
    ada
    0.46
     Next
    0.46
     \$
    0.46
     Mail
    0.44
     Letter
    0.44
     Copyright
    0.44
     Staff
    0.44
    Activations Density 0.000%

    No Known Activations