© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6672
    Prev
    Next
    INDEX
    Explanations

    mentions of Air Jordan shoes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ########.
    -0.94
     @"/
    -0.91
    AndEndTag
    -0.85
     estimés
    -0.84
    ValueStyle
    -0.82
     "..\..\
    -0.82
     "..\..\..\
    -0.80
    devamını
    -0.78
    сылкі
    -0.78
     AttributeSet
    -0.78
    POSITIVE LOGITS
     col
    0.48
     Plan
    0.42
    nění
    0.40
    Plan
    0.40
    indon
    0.39
     Des
    0.39
     Col
    0.38
     мной
    0.38
    miş
    0.38
    cestershire
    0.38
    Activations Density 0.639%

    No Known Activations