© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13504
    Prev
    Next
    INDEX
    Explanations

    words common to the purchase or download computer games

    oai_token-act-pair · gemini-2.0-flash

    Online shopping terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    deus
    -0.49
    //
    -0.46
    PutMapping
    -0.44
     Federation
    -0.43
     AssemblyTitle
    -0.43
    cyd
    -0.43
     ganglion
    -0.42
     coda
    -0.42
    leneck
    -0.42
    Referencias
    -0.40
    POSITIVE LOGITS
     Wishlist
    0.59
     Halal
    0.59
    featureID
    0.57
     Coupons
    0.56
    bootstrapcdn
    0.56
     Cheaper
    0.53
    GOTREF
    0.52
     balconies
    0.52
     kios
    0.52
     SHOPPING
    0.51
    Activations Density 6.914%

    No Known Activations