© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 12734
    Prev
    Next
    INDEX
    Explanations

    double underscores in code

    oai_token-act-pair · gemini-2.0-flash

    __

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ".
    
    -0.98
    Personensuche
    -0.98
    }")
    
    -0.94
    "]);
    
    -0.88
    "))
    
    -0.86
    WriteTagHelper
    -0.86
     __
    -0.85
    }.
    
    -0.84
    ).
    
    -0.83
     الاطلاع
    -0.83
    POSITIVE LOGITS
    “
    0.77
    #
    0.62
    /
    0.52
    -
    0.52
     an
    0.51
     the
    0.49
    onAttach
    0.47
    –
    0.47
     daarom
    0.45
     a
    0.43
    Activations Density 0.373%

    No Known Activations