© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138851
    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_37_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
     Map
    0.41
     Bez
    0.40
     پ
    0.40
     z
    0.39
     Conf
    0.39
     Zin
    0.38
    łon
    0.37
     secret
    0.36
     Tal
    0.36
     BSA
    0.36
    POSITIVE LOGITS
    हुआ
    0.42
    িউ
    0.39
    ichts
    0.38
     dailySales
    0.38
    rieron
    0.38
     inaugurated
    0.37
     essais
    0.37
    徠
    0.37
     ممال
    0.37
    гел
    0.37
    Activations Density 0.000%

    No Known Activations