© 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-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10619
    Prev
    Next
    INDEX
    Explanations

    superlative descriptions in sports and reward programs

    oai_token-act-pair · gemini-2.0-flash

    Groups and rankings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.82
    
    -0.56
    dumps
    -0.52
    AsStream
    -0.49
     viewDidLoad
    -0.49
    chuck
    -0.48
    ObjectContext
    -0.48
     Âge
    -0.47
     ویکی‌پدیای
    -0.47
     JsonResponse
    -0.47
    POSITIVE LOGITS
     насељу
    0.53
     peix
    0.50
    Зву
    0.48
    Général
    0.48
    SequentialGroup
    0.46
     ó
    0.46
    Numerology
    0.45
    igraphy
    0.45
    iastical
    0.44
    gesamt
    0.44
    Activations Density 0.694%

    No Known Activations