© 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. 15814
    Prev
    Next
    INDEX
    Explanations

    tokens related to personal opinions about products and the value provided to the customers.

    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
    הערות
    -0.71
    RenderAtEndOf
    -0.62
    Vaata
    -0.62
     numberOfRows
    -0.61
    ^(@)
    -0.60
     textStatus
    -0.60
    prepareStatement
    -0.60
    enseignements
    -0.59
    Cordialement
    -0.59
     CreateTagHelper
    -0.59
    POSITIVE LOGITS
    EndContext
    0.50
     Eisenberg
    0.46
     تضيفلها
    0.46
     of
    0.44
     sexually
    0.44
     financially
    0.42
    だけに
    0.40
     here
    0.40
    KeyPressed
    0.40
    my
    0.39
    Activations Density 18.960%

    No Known Activations