© 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. 201168
    Prev
    Next
    INDEX
    Explanations

    pro-rated degradation or loss

    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
    꽤
    0.25
    thisTrack
    0.25
     ہوں۔
    0.25
    ПР
    0.25
    UMBIA
    0.24
    Proveedor
    0.24
    łą
    0.24
     proveedor
    0.24
     Пре
    0.24
    Providers
    0.24
    POSITIVE LOGITS
      
    0.30
    e
    0.30
    mines
    0.28
    يان
    0.27
     for
    0.26
    ᓂ
    0.26
    ا
    0.26
    en
    0.25
    اكم
    0.25
    aline
    0.25
    Activations Density 0.001%

    No Known Activations