© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12039
    Prev
    Next
    INDEX
    Explanations

    words related to "ischemic" and also the suffix "och", possibly related to a specific scientific term

    oai_token-act-pair · gemini-2.0-flash

    scientific/medical writing

    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
     Kowal
    -0.60
     oldValue
    -0.55
    LECTION
    -0.52
     pecu
    -0.52
    之一
    -0.50
     Cair
    -0.50
    ervos
    -0.50
     conduce
    -0.48
    ABOR
    -0.48
    HtmlAttribute
    -0.48
    POSITIVE LOGITS
    <bos>
    0.93
    sizeCache
    0.75
     Is
    0.74
    Is
    0.67
     ISNI
    0.63
     ویکی‌پدیا
    0.63
     IS
    0.62
    Aholisi
    0.61
     ModelExpression
    0.60
    LookAnd
    0.59
    Activations Density 0.842%

    No Known Activations