© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11943
    Prev
    Next
    INDEX
    Explanations

    the word "writing" and terms associated with scholarly articles

    oai_token-act-pair · gemini-2.0-flash

    writing

    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
     Jefus
    -1.47
     myſelf
    -1.37
     Efq
    -1.29
    ſelves
    -1.27
     Theſe
    -1.27
     itſelf
    -1.26
    ſelf
    -1.24
     houſe
    -1.23
     Eſ
    -1.22
     pleaſure
    -1.21
    POSITIVE LOGITS
    льни
    0.56
    ↵
    0.56
     "
    0.55
    жи
    0.55
    <em>
    0.55
    TALL
    0.54
    <bos>
    0.52
    culin
    0.51
    жина
    0.50
    ruta
    0.49
    Activations Density 0.935%

    No Known Activations