© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8216
    Prev
    Next
    INDEX
    Explanations

    words relating to work, job applications questions or descriptions.

    oai_token-act-pair · gemini-2.0-flash

    Expressing a request

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    HtmlAttribute
    -0.63
    ண்டும்
    -0.55
     Lightboxes
    -0.55
    ?");
    -0.54
     smtplib
    -0.52
    mbggenerated
    -0.51
     unknownFields
    -0.50
    "=>$
    -0.50
     Italijani
    -0.49
    RegistryLite
    -0.48
    POSITIVE LOGITS
     try
    1.05
     don
    0.96
     take
    0.95
     please
    0.94
     let
    0.93
    please
    0.87
     keep
    0.86
     go
    0.84
     check
    0.82
     dont
    0.81
    Activations Density 4.453%

    No Known Activations