© 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. 49262
    Prev
    Next
    INDEX
    Explanations

    thanks for

    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
    legisl
    0.37
    ্বিত
    0.37
    ಓ
    0.36
    غرافيا
    0.36
     Сти
    0.36
     אר
    0.35
     цу
    0.35
     стиля
    0.35
     aristocratic
    0.35
    极其
    0.35
    POSITIVE LOGITS
     membantu
    0.35
     decompression
    0.34
    పరి
    0.34
    벼
    0.33
     bantuan
    0.33
     Shining
    0.33
    resti
    0.32
     عزی
    0.32
     معاون
    0.32
     Mr
    0.32
    Activations Density 0.001%

    No Known Activations