© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200958
    Prev
    Next
    INDEX
    Explanations

    jsx syntax

    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_12_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
    icznej
    0.53
    вии
    0.53
    x
    0.52
     improb
    0.52
    শ্রেণীর
    0.52
    elled
    0.51
     использованием
    0.51
    utip
    0.50
     DataType
    0.50
    coherent
    0.50
    POSITIVE LOGITS
    ská
    0.56
    љи
    0.55
    
    0.54
     EQS
    0.53
    hrm
    0.50
    ಿಸುವ
    0.49
    কথা
    0.49
    ską
    0.48
    蓿
    0.48
    bands
    0.48
    Activations Density 0.000%

    No Known Activations