© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91829
    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_11_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
     animating
    0.52
    });
    0.51
     enam
    0.50
     getContentPane
    0.49
     emphasises
    0.49
    τώ
    0.48
    mobilpay
    0.47
     affords
    0.47
     შესაძ
    0.47
     hatches
    0.47
    POSITIVE LOGITS
    Crime
    0.56
     Cancer
    0.55
     Voltage
    0.54
     Research
    0.54
    S
    0.52
     Status
    0.52
     Resolution
    0.52
    is
    0.51
     Applications
    0.51
    AES
    0.51
    Activations Density 0.000%

    No Known Activations