© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3654
    Prev
    Next
    INDEX
    Explanations

    special characters or markers

    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_40_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
    MRC
    0.37
    𝜁
    0.34
     Дж
    0.34
     Mesopotamia
    0.34
     Юрий
    0.34
     MRC
    0.33
     DSM
    0.33
    푚
    0.33
    <0xF4>
    0.32
     Спорт
    0.32
    POSITIVE LOGITS
    orthin
    0.35
     stringWith
    0.35
     disposer
    0.35
    netstandard
    0.34
    idad
    0.34
    ége
    0.34
    zione
    0.34
    iest
    0.33
    ful
    0.33
    swering
    0.33
    Activations Density 0.240%

    No Known Activations