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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4299
    Prev
    Next
    INDEX
    Explanations

    the phrase "had" or "having"

    oai_token-act-pair · gemini-2.0-flash

    d in brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     متعلقه
    -0.73
     Roskov
    -0.63
    ViewImports
    -0.63
     كومونز
    -0.62
    GEBURTS
    -0.62
    odotus
    -0.61
    loem
    -0.60
    ariously
    -0.60
     imageNamed
    -0.59
    ContentAsync
    -0.59
    POSITIVE LOGITS
     had
    1.70
     has
    1.50
     have
    1.50
    <bos>
    1.48
     Have
    1.44
    Have
    1.39
    have
    1.35
    had
    1.30
     Had
    1.28
    Had
    1.28
    Activations Density 0.275%

    No Known Activations