© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12846
    Prev
    Next
    INDEX
    Explanations

    words related to medical contexts as well as children

    oai_token-act-pair · gemini-2.0-flash

    doctor

    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
     ويكيميديا
    -0.86
    Reentrant
    -0.83
     archaeologists
    -0.82
    nachron
    -0.81
    NewGuid
    -0.81
    ilitar
    -0.79
    Filmografie
    -0.79
     veterinarians
    -0.77
    thâu
    -0.77
     dentists
    -0.77
    POSITIVE LOGITS
    <bos>
    0.95
    '
    0.70
    The
    0.67
    ↵↵
    0.65
    3
    0.65
    <i>
    0.62
    1
    0.62
    })));
    0.60
    2
    0.60
    4
    0.59
    Activations Density 1.378%

    No Known Activations