© 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. 52246
    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
    氾
    0.40
    跎
    0.38
     raged
    0.38
     વ્ય
    0.37
    BIT
    0.37
    叱
    0.36
    exo
    0.36
    тится
    0.36
     ('
    0.36
     entsprechen
    0.36
    POSITIVE LOGITS
    了解
    0.44
     Knowledge
    0.43
     knowledge
    0.40
    knowledge
    0.40
     Luk
    0.39
     pipelines
    0.39
    ̯
    0.39
     enjoyable
    0.38
    know
    0.37
     Mondays
    0.37
    Activations Density 0.000%

    No Known Activations