© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207330
    Prev
    Next
    INDEX
    Explanations

    cathedral

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Colts
    0.46
    ⎢
    0.42
    tgts
    0.41
    মতী
    0.40
    মতি
    0.39
     Glob
    0.39
    ajib
    0.38
    齡
    0.38
     Colt
    0.37
     दिलीप
    0.37
    POSITIVE LOGITS
     cathedral
    1.23
     Cathedral
    1.23
     catedral
    1.19
     Catedral
    1.04
     kated
    1.01
    Cat
    0.91
     Cat
    0.90
     cathe
    0.89
     Cath
    0.86
     cath
    0.82
    Activations Density 0.000%

    No Known Activations