© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5103
    Prev
    Next
    INDEX
    Explanations

    phrases including numbers and the word "speed," also some phrases indicative of historical events and conflicts

    oai_token-act-pair · gemini-2.0-flash

    car gearboxes and speed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     للاسماء
    -0.66
    RenderAtEndOf
    -0.62
    ]--;
    -0.57
    hela
    -0.54
     Pata
    -0.52
     getResources
    -0.52
     dela
    -0.50
    icolon
    -0.50
    rophoto
    -0.49
     passing
    -0.49
    POSITIVE LOGITS
     beginnetje
    0.68
    <?
    0.61
    #
    0.56
     通販
    0.56
    /*
    0.56
    RectangleBorder
    0.55
    Przypisy
    0.53
     actuelles
    0.52
     appelez
    0.52
     éti
    0.52
    Activations Density 0.802%

    No Known Activations