© 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. 12282
    Prev
    Next
    INDEX
    Explanations

    java code blocks

    oai_token-act-pair · gemini-2.0-flash

    Java code

    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
    complexContent
    -0.98
     للمعارف
    -0.96
     كومونز
    -0.83
    kháu
    -0.81
    djangoproject
    -0.75
    
    -0.75
    sizeCache
    -0.73
    Rptr
    -0.73
    manteau
    -0.69
    NUMX
    -0.68
    POSITIVE LOGITS
    Visita
    0.40
     cận
    0.40
    Enlaces
    0.40
     e
    0.40
     b
    0.38
    conv
    0.38
     dita
    0.38
    tuig
    0.38
    car
    0.37
    گیر
    0.37
    Activations Density 2.138%

    No Known Activations