© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10985
    Prev
    Next
    INDEX
    Explanations

    words used in specialized contexts like medical, legal or technical writing

    oai_token-act-pair · gemini-2.0-flash

    Medical/Research Text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -0.72
    IsContent
    -0.55
     Sito
    -0.53
     itſelf
    -0.53
     تانيه
    -0.53
    ską
    -0.52
    ')"
    -0.51
     ]}
    -0.50
    }\}
    -0.50
    '"
    -0.49
    POSITIVE LOGITS
    CPtr
    0.58
    Bronnen
    0.58
    ftagPool
    0.56
    ɵɵ
    0.55
    Lähteet
    0.55
    Referències
    0.54
    וויק
    0.54
    Παραπομπές
    0.54
    клопе
    0.52
     igång
    0.52
    Activations Density 26.616%

    No Known Activations