© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3182
    Prev
    Next
    INDEX
    Explanations

    the words "behalf", "authority", "passive", "record", "theory", "evidence", "file", "category", "side", and "story"

    oai_token-act-pair · gemini-2.0-flash

    legal/political standpoints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    peutic
    -0.60
     Administrativna
    -0.59
    IsPostBack
    -0.58
     estimés
    -0.53
     Waray
    -0.53
     kanya
    -0.52
    存于互联网档案馆
    -0.52
    zzlement
    -0.51
    DoubleQuotes
    -0.51
     getConnection
    -0.51
    POSITIVE LOGITS
    setVerticalGroup
    0.71
     snippetHide
    0.71
     AssemblyProduct
    0.62
    AddHtmlAttribute
    0.62
     rêver
    0.60
     auquel
    0.58
     Intu
    0.57
     sév
    0.56
     exécu
    0.56
    WithMany
    0.56
    Activations Density 2.914%

    No Known Activations