© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6306
    Prev
    Next
    INDEX
    Explanations

    references to sugar

    oai_token-act-pair · gemini-2.0-flash

    sugar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    UGA
    -0.53
     writeTo
    -0.52
    HasAnnotation
    -0.52
    HasForeignKey
    -0.50
    toContain
    -0.47
    SerializedName
    -0.45
    upe
    -0.45
    uur
    -0.45
    /***/
    -0.44
    กรณ์
    -0.44
    POSITIVE LOGITS
     يتيمه
    0.74
    kháu
    0.67
    Erreferentziak
    0.66
    aarrggbb
    0.65
    WebVitals
    0.57
    LogFactory
    0.57
    Хьажоргаш
    0.57
    äsident
    0.57
     Administrativna
    0.56
    tierrez
    0.55
    Activations Density 1.784%

    No Known Activations