© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223720
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    IPSET
    0.64
     intelligents
    0.63
    i
    0.61
    이면
    0.61
     sympathize
    0.57
     thoughtful
    0.55
     idiosyncratic
    0.55
     occupé
    0.55
     endearing
    0.54
     ニュー
    0.54
    POSITIVE LOGITS
     Biggest
    0.55
    </h2>
    0.53
    utc
    0.52
    ut
    0.49
    LAND
    0.48
    诗
    0.48
    ct
    0.47
    un
    0.47
    aj
    0.47
    ben
    0.47
    Activations Density 0.000%

    No Known Activations