© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236092
    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_32_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
    ResultMessage
    0.42
    饺
    0.39
     mirando
    0.38
     مە
    0.38
     obserw
    0.37
     दही
    0.37
     preparados
    0.37
    广场
    0.36
     عرف
    0.36
     tanggung
    0.36
    POSITIVE LOGITS
    noise
    0.42
     Noise
    0.40
    ually
    0.38
    Noise
    0.38
    pop
    0.36
    捱
    0.36
     dispel
    0.36
    噪音
    0.36
     Chaplin
    0.35
    Multiply
    0.35
    Activations Density 0.000%

    No Known Activations