© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215583
    Prev
    Next
    INDEX
    Explanations

    programming context markers

    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_31_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
    روں
    0.35
    ichannel
    0.35
    fromCharCode
    0.35
    ઢ
    0.35
     تعليم
    0.34
     garantia
    0.34
    ManyToManyField
    0.33
    estim
    0.33
     lado
    0.32
    angka
    0.32
    POSITIVE LOGITS
    単
    0.34
    Grab
    0.33
    잡
    0.33
    とに
    0.32
     옮
    0.31
    Leg
    0.31
    
    0.31
    
    0.30
    􏰁
    0.30
     बस
    0.30
    Activations Density 0.000%

    No Known Activations