© 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. 12156
    Prev
    Next
    INDEX
    Explanations

    the word "prove" and also some code related to "pods."

    oai_token-act-pair · gemini-2.0-flash

    proving, validation

    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
    KEYCODE
    -0.63
     ​​
    -0.63
    ftagPool
    -0.62
     الاطلاع
    -0.59
     Jerusalén
    -0.58
    runApp
    -0.54
    medriver
    -0.54
    .*")]
    -0.54
    Źródło
    -0.53
    CultureInfo
    -0.53
    POSITIVE LOGITS
    ostoma
    0.69
    XmlAccessType
    0.67
     Boud
    0.66
     متعلقه
    0.64
     CiNii
    0.63
     Waray
    0.60
    omenclature
    0.60
    ضايا
    0.60
     Teich
    0.57
    spher
    0.55
    Activations Density 0.419%

    No Known Activations