Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14649
    Prev
    Next
    INDEX
    Explanations

    references to periods of time

    oai_token-act-pair · gemini-2.0-flash

    units of time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    tagHelperRunner
    -0.78
    thâu
    -0.69
    MigrationBuilder
    -0.63
    /******/
    -0.61
    AddTagHelper
    -0.60
    انيف
    -0.59
    enumii
    -0.56
    ngrx
    -0.55
    PyTuple
    -0.54
     typelib
    -0.54
    POSITIVE LOGITS
     beyond
    0.93
     preceding
    0.92
     thereafter
    0.85
     afterwards
    0.84
     before
    0.84
     below
    0.83
     afterward
    0.83
     above
    0.82
    beyond
    0.81
     ahead
    0.80
    Activations Density 2.391%

    No Known Activations