© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11590
    Prev
    Next
    INDEX
    Explanations

    the word "service" and related words like "services" and "providers"

    oai_token-act-pair · gemini-2.0-flash

    service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -0.77
    ...
    -0.73
    /
    -0.69
    <eos>
    -0.68
     (
    -0.66
    .
    -0.66
    ~
    -0.65
     a
    -0.64
     F
    -0.63
     The
    -0.63
    POSITIVE LOGITS
     Efq
    1.67
     ―――――
    1.55
     myſelf
    1.52
     itſelf
    1.48
     Jefus
    1.46
     iſt
    1.45
     pleaſure
    1.44
     raiſ
    1.39
     Reſ
    1.38
     ſche
    1.36
    Activations Density 0.092%

    No Known Activations