© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50821
    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_55_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
     shooters
    0.35
     overnight
    0.35
     ලි
    0.35
     MINUTES
    0.34
     परफेक्ट
    0.34
    応
    0.34
     shooter
    0.34
    不做
    0.34
    随
    0.34
    増
    0.33
    POSITIVE LOGITS
    ふる
    0.43
    étique
    0.41
    ettivo
    0.40
    otle
    0.39
     एकल
    0.38
    propyl
    0.38
    anska
    0.38
    rather
    0.38
     representan
    0.38
    ewell
    0.38
    Activations Density 0.000%

    No Known Activations