© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77233
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and units (GB)

    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
     $\
    0.41
     $/
    0.38
    തൃ
    0.38
    语
    0.34
     păr
    0.34
     കി
    0.34
     $=$
    0.34
    สัก
    0.34
     bottom
    0.33
     conversational
    0.33
    POSITIVE LOGITS
     useSelector
    0.40
    </caption>
    0.39
     повлия
    0.38
     இந்தக்
    0.37
    ফল
    0.37
     puestos
    0.37
    隗
    0.36
    ́a
    0.36
    AMD
    0.36
     conces
    0.36
    Activations Density 0.000%

    No Known Activations