© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133487
    Prev
    Next
    INDEX
    Explanations

    abilities, types

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     бассе
    0.36
     $\|
    0.34
     (()
    0.33
     $\
    0.33
     مخ
    0.33
     w
    0.32
     med
    0.32
    ➋
    0.32
     grow
    0.31
     φ
    0.31
    POSITIVE LOGITS
    ­
    0.42
    ancial
    0.42
     धान
    0.41
    ién
    0.40
    營業
    0.40
    ürdig
    0.39
     সম্পর্কের
    0.39
    
    0.38
    িয়াছিল
    0.38
    ıma
    0.38
    Activations Density 0.102%

    No Known Activations