© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11420
    Prev
    Next
    INDEX
    Explanations

    the word "loaded" and its variants

    oai_token-act-pair · gemini-2.0-flash

    loaded

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    +#+#
    -1.20
    PerformLayout
    -1.15
    providedIn
    -1.13
    expandindo
    -1.11
    PreferredItem
    -1.09
    IntoConstraints
    -1.09
    AndEndTag
    -1.08
    DockStyle
    -1.01
     ModelExpression
    -1.01
     متعلقه
    -1.00
    POSITIVE LOGITS
     Jérusalem
    0.60
     africaine
    0.55
     hâte
    0.55
     chrétienne
    0.54
     chré
    0.54
     ainfi
    0.53
    es
    0.52
     obicei
    0.52
     sûr
    0.52
     Syrie
    0.51
    Activations Density 1.936%

    No Known Activations