© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11635
    Prev
    Next
    INDEX
    Explanations

    the word "app" or content related to shopping and online transactions.

    oai_token-act-pair · gemini-2.0-flash

    making choices/purchases

    np_max-act-logits · 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
     calendriers
    -0.72
     länge
    -0.59
     Obispo
    -0.55
    tvguidetime
    -0.54
     umano
    -0.54
    Hombre
    -0.53
    glGen
    -0.52
     varandra
    -0.51
     myndig
    -0.51
    pubs
    -0.51
    POSITIVE LOGITS
    TintMode
    0.59
     conduct
    0.58
    TestFixture
    0.57
    rungsseite
    0.55
    AndEndTag
    0.55
     focus
    0.54
    úrate
    0.52
     dwell
    0.51
     Seel
    0.50
     opt
    0.49
    Activations Density 2.625%

    No Known Activations