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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10064
    Prev
    Next
    INDEX
    Explanations

    the verb "enter" (and variants) along with prepositions.

    oai_token-act-pair · gemini-2.0-flash

    enter

    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
    openqa
    -0.70
    Xna
    -0.52
     الحره
    -0.51
    httphttps
    -0.48
     vuitton
    -0.47
     conseguenza
    -0.46
    PrivateRoute
    -0.46
     ✭✭
    -0.46
     Partici
    -0.45
     AssemblyTitle
    -0.45
    POSITIVE LOGITS
     into
    1.03
     INTO
    0.82
    into
    0.76
    INTO
    0.74
     Into
    0.72
    Into
    0.71
    клопе
    0.62
    ArgumentParser
    0.62
    IntoConstraints
    0.61
    tainers
    0.51
    Activations Density 2.117%

    No Known Activations