© 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. 59234
    Prev
    Next
    INDEX
    Explanations

    emerge, emergent

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ור
    0.77
    ים
    0.77
    s
    0.71
    েন
    0.61
    en
    0.61
     laborer
    0.60
     state
    0.60
     он
    0.60
    м
    0.59
     orifice
    0.57
    POSITIVE LOGITS
    5
    1.04
    8
    0.89
    4
    0.89
    6
    0.80
    *
    0.72
    ua
    0.70
    <
    0.70
    7
    0.70
    Code
    0.68
                    
    0.67
    Activations Density 0.003%

    No Known Activations