© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176451
    Prev
    Next
    INDEX
    Explanations

    focus and outline

    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_24_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
     --
    0.42
     HOW
    0.37
     แม
    0.37
     Mitra
    0.37
    >-->
    0.36
     most
    0.36
    s
    0.36
     सेक्सी
    0.35
    ；
    0.35
    com
    0.34
    POSITIVE LOGITS
     recibieron
    0.48
    uyeron
    0.44
    嚟
    0.41
    QTTR
    0.41
    増や
    0.41
    🙏🏻
    0.40
    ImgBoard
    0.40
     ойношот
    0.40
    ቷ
    0.39
    ຍ
    0.39
    Activations Density 0.000%

    No Known Activations