© 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. 4679
    Prev
    Next
    INDEX
    Explanations

    indicators of time or relationships between clauses

    oai_token-act-pair · gemini-2.0-flash

    connecting clauses and sentences

    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
     them
    -3.20
    them
    -2.52
     THEM
    -1.99
     eux
    -1.59
     Them
    -1.55
    Them
    -1.55
     них
    -1.52
     ihnen
    -1.45
     him
    -1.40
     They
    -1.40
    POSITIVE LOGITS
    次的
    0.49
    mär
    0.44
     he
    0.42
     we
    0.41
    次
    0.41
     эта
    0.40
     यह
    0.39
     οι
    0.38
    মান
    0.38
    #
    0.37
    Activations Density 3.406%

    No Known Activations