© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177695
    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_50_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
     somehow
    0.59
     Somehow
    0.50
     somew
    0.38
     cím
    0.38
    উ
    0.37
     entlang
    0.37
    urnya
    0.36
    ');?>
    0.36
     кандай
    0.35
    вні
    0.35
    POSITIVE LOGITS
     cater
    0.42
     hence
    0.40
    Hence
    0.39
     catering
    0.38
     catered
    0.38
    lett
    0.38
     CAT
    0.37
     Schott
    0.37
    qat
    0.36
    hence
    0.36
    Activations Density 0.000%

    No Known Activations