© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79890
    Prev
    Next
    INDEX
    Explanations

    Nurhaci, emojis 🙈

    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_0_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
    s
    1.80
    the
    1.48
    ۰
    1.46
     have
    1.44
     as
    1.39
    have
    1.39
    0
    1.32
     for
    1.28
     de
    1.18
     by
    1.13
    POSITIVE LOGITS
    ت
    1.88
    ア
    1.45
    م
    1.43
    很
    1.42
    ot
    1.35
    </h4>
    1.34
    ம்
    1.34
    </h2>
    1.32
    ように
    1.28
    it
    1.27
    Activations Density 0.000%

    No Known Activations