© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2709
    Prev
    Next
    INDEX
    Explanations

    technical writing related to patents and inventions, especially phrases like "in accordance with the present invention".

    oai_token-act-pair · gemini-2.0-flash

    words related to devices and technology

    np_token-act-pair-logits · gpt-4o-mini

    Technical descriptions of parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    EndContext
    -0.96
    enumii
    -0.83
     Wikimédia
    -0.79
    uxxxx
    -0.75
     المعيارى
    -0.71
    
    -0.71
    
    -0.71
    PyExc
    -0.70
    WebVitals
    -0.68
    /*
    -0.68
    POSITIVE LOGITS
     top
    0.45
    蠢
    0.44
    κό
    0.43
    paign
    0.43
    ämän
    0.42
    tuta
    0.40
     pass
    0.40
     Corte
    0.39
     bait
    0.39
    Tempat
    0.39
    Activations Density 20.944%

    No Known Activations