© 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. 668
    Prev
    Next
    INDEX
    Explanations

    is related to numbers and measures, particularly in relation to "is" or "are."

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    RegressionTest
    -0.63
    =?";
    -0.59
    клопе
    -0.55
    Geplaatst
    -0.53
    INCLUDED
    -0.52
    جغرافيا
    -0.52
    Personensuche
    -0.51
    cendental
    -0.51
    niosek
    -0.50
     continúas
    -0.50
    POSITIVE LOGITS
     in
    1.69
     In
    0.83
    In
    0.80
    in
    0.77
     في
    0.68
     si
    0.64
     daca
    0.62
    inthe
    0.61
     в
    0.60
     into
    0.60
    Activations Density 1.901%

    No Known Activations