© 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. 10999
    Prev
    Next
    INDEX
    Explanations

    words describing inventions and their components

    oai_token-act-pair · gemini-2.0-flash

    inventions and technology

    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
    entuh
    -0.43
     hendes
    -0.40
     diatas
    -0.39
     wireType
    -0.39
     IMDG
    -0.38
    UrlResolution
    -0.38
     ويل
    -0.38
    gub
    -0.37
    وصلات
    -0.36
     poivre
    -0.36
    POSITIVE LOGITS
    ConstraintMaker
    0.87
    
    0.81
     pinulongan
    0.80
    oa̍t
    0.76
     الرياضيه
    0.71
    VIAF
    0.70
    KommentareTeilen
    0.67
    EndInit
    0.66
     ***!
    0.66
     MainAxisSize
    0.65
    Activations Density 7.116%

    No Known Activations