© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5711
    Prev
    Next
    INDEX
    Explanations

    the word "producer" and nearby associated words

    oai_token-act-pair · gemini-2.0-flash

    producer

    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
    NOK
    -0.59
     Occupations
    -0.59
     onCreateView
    -0.59
    OPP
    -0.58
    already
    -0.58
     ^
    -0.57
    <eos>
    -0.57
     sein
    -0.56
    commut
    -0.55
    __*/
    -0.55
    POSITIVE LOGITS
     Efq
    1.53
    ſelf
    1.42
     Diſ
    1.39
     Monfieur
    1.37
     houſe
    1.35
     purpoſe
    1.33
     Majefty
    1.32
     Jefus
    1.30
     myſelf
    1.30
     himſelf
    1.27
    Activations Density 0.744%

    No Known Activations