© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47186
    Prev
    Next
    INDEX
    Explanations

    let's talk about

    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_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
    أي
    0.16
     aşağıdaki
    0.16
    <0x80>
    0.15
     vermiş
    0.15
     mago
    0.15
     darle
    0.14
    ورك
    0.14
     příjem
    0.14
     conos
    0.14
     prepend
    0.14
    POSITIVE LOGITS
    settes
    0.15
    gel
    0.15
    ni
    0.15
    h
    0.14
    kom
    0.13
    ль
    0.13
    cyte
    0.13
    ją
    0.13
    taş
    0.13
    na
    0.13
    Activations Density 0.150%

    No Known Activations