© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13388
    Prev
    Next
    INDEX
    Explanations

    words related to customer service and positive attributes related generally to people

    oai_token-act-pair · gemini-2.0-flash

    people assisting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    enumi
    -0.66
    AndEndTag
    -0.63
     EconPapers
    -0.60
    enumii
    -0.56
    toggler
    -0.55
    出版年
    -0.54
    expandindo
    -0.52
     resourceCulture
    -0.49
    TintMode
    -0.49
     sti
    -0.49
    POSITIVE LOGITS
     utafiti
    0.59
    NSIndexPath
    0.52
    ancing
    0.52
     explained
    0.52
     parlent
    0.49
     الدولى
    0.49
    duje
    0.49
    passing
    0.48
     homology
    0.48
    ริง
    0.48
    Activations Density 6.379%

    No Known Activations