© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80634
    Prev
    Next
    INDEX
    Explanations

    exquisite objects and descriptions

    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
    지
    1.58
    <0x80>
    1.27
     сфер
    1.26
    지에
    1.24
    ม
    1.23
    ють
    1.16
    지와
    1.16
     liczb
    1.15
    ین
    1.13
    ק
    1.13
    POSITIVE LOGITS
    </h2>
    1.73
     have
    1.67
    <0x0D>
    1.60
    ni
    1.57
    ни
    1.55
    ،
    1.52
    </b>
    1.49
    at
    1.49
    ，
    1.47
    </h3>
    1.45
    Activations Density 0.000%

    No Known Activations