© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12704
    Prev
    Next
    INDEX
    Explanations

    legal citations containing the letter "d."

    oai_token-act-pair · gemini-2.0-flash

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    يكب
    -0.60
    PreferredItem
    -0.59
     للمعارف
    -0.54
    GeneratedCode
    -0.53
    liferay
    -0.53
     mourut
    -0.52
    makeText
    -0.52
     سكانية
    -0.51
     automatiques
    -0.49
    MessageOf
    -0.48
    POSITIVE LOGITS
    VersionUID
    0.60
    ALTERN
    0.59
    <![
    0.58
    TestingModule
    0.55
    ورش
    0.54
    atelli
    0.54
    terday
    0.51
    eaway
    0.51
    rimp
    0.51
     }}$}
    0.50
    Activations Density 1.404%

    No Known Activations