© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44660
    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_22_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
     डोनाल्ड
    0.46
    PubMed
    0.44
    éticos
    0.41
    ].)
    0.41
    Donald
    0.41
    leveland
    0.41
    Mozilla
    0.40
    servername
    0.39
     lacked
    0.39
    ）；
    0.39
    POSITIVE LOGITS
    startsWith
    0.42
     seasonal
    0.41
     infer
    0.41
    がら
    0.41
    Seasonal
    0.39
     Veer
    0.38
    銳
    0.38
     tempr
    0.37
     egensk
    0.37
     proport
    0.37
    Activations Density 0.000%

    No Known Activations