© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10368
    Prev
    Next
    INDEX
    Explanations

    verbs of being/existing

    oai_token-act-pair · gemini-2.0-flash

    reported speech

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     lenker
    -0.68
    ksessa
    -0.65
    WebServlet
    -0.63
    tvguidetime
    -0.63
    protoc
    -0.60
    <?
    -0.60
    AsStream
    -0.57
    ništvo
    -0.57
    Välislingid
    -0.57
    Šaltiniai
    -0.57
    POSITIVE LOGITS
     said
    2.27
    said
    1.80
     thought
    1.80
     believed
    1.56
     SAID
    1.52
    thought
    1.50
    Thought
    1.48
    Said
    1.47
     Thought
    1.46
     Said
    1.45
    Activations Density 8.481%

    No Known Activations