© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3075
    Prev
    Next
    INDEX
    Explanations

    equations and mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    Code and mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    pointers
    -0.60
    oredCriteria
    -0.58
    legs
    -0.58
    Демографія
    -0.57
    GEBURTSDATUM
    -0.57
    DoubleQuotes
    -0.56
     vPvB
    -0.55
    ejs
    -0.54
    octanol
    -0.54
    grip
    -0.53
    POSITIVE LOGITS
     autorytatywna
    0.54
     faptul
    0.49
    ########.
    0.47
    ConstraintMaker
    0.47
     ")");
    0.47
     MonoBehaviour
    0.46
     atlan
    0.46
     femei
    0.45
    WEBPACK
    0.45
     communiquez
    0.43
    Activations Density 1.020%

    No Known Activations