© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2353
    Prev
    Next
    INDEX
    Explanations

    words that seem to be headings in technical documents

    oai_token-act-pair · gemini-2.0-flash

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     may
    -0.49
     can
    -0.49
    stdc
    -0.47
     general
    -0.44
     continuant
    -0.44
    xmlhttp
    -0.42
     didn
    -0.42
     oma
    -0.41
     pal
    -0.40
     sub
    -0.40
    POSITIVE LOGITS
     Efq
    1.04
     Majefty
    1.02
     myſelf
    1.01
     itſelf
    0.96
     Monfieur
    0.96
     Jefus
    0.95
     Houſe
    0.94
    ſelf
    0.93
    ſelves
    0.91
     pleaſure
    0.91
    Activations Density 3.885%

    No Known Activations