© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37632
    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_57_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
    纜
    0.42
    врат
    0.40
     ficam
    0.39
    agnet
    0.37
    𝙋
    0.37
     ]),
    0.37
    abhut
    0.37
    Predictions
    0.37
    peanut
    0.36
    湧
    0.36
    POSITIVE LOGITS
     kindly
    0.36
     en
    0.35
     pictures
    0.35
     merchant
    0.35
     qui
    0.35
    លើ
    0.34
     add
    0.34
     specialty
    0.34
     m
    0.34
     kina
    0.34
    Activations Density 0.000%

    No Known Activations