© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4318
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with medical treatments and facilities, especially surgery

    oai_token-act-pair · gemini-2.0-flash

    Negative sentiment/difficult situation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     per
    -0.51
    地の
    -0.48
    élie
    -0.46
     More
    -0.45
    nvarchar
    -0.45
    ApiModelProperty
    -0.45
    iteln
    -0.44
    iers
    -0.44
    Ge
    -0.44
    まん
    -0.44
    POSITIVE LOGITS
    ViewFeatures
    0.90
    CodedInputStream
    0.88
    出版年
    0.82
     itſelf
    0.79
     pleaſure
    0.78
     ostavi
    0.75
    anmoins
    0.73
    enumi
    0.73
    enumii
    0.72
     صوتيه
    0.72
    Activations Density 35.524%

    No Known Activations