© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16042
    Prev
    Next
    INDEX
    Explanations

    words used describing formal settings, historical writings, treaties and testimonies

    oai_token-act-pair · gemini-2.0-flash

    legal, historical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     للاسماء
    -1.08
     kasarigan
    -1.07
    Personendaten
    -0.94
     AssemblyCulture
    -0.84
     виправивши
    -0.82
    
    -0.75
     فريبيس
    -0.75
     مشين
    -0.73
    ValueStyle
    -0.72
    ⓧ
    -0.71
    POSITIVE LOGITS
     fitting
    0.60
     of
    0.57
    <caption>
    0.49
    ENDENT
    0.48
    fitting
    0.46
     touching
    0.44
     kept
    0.44
     Fitting
    0.44
    rouse
    0.43
     useful
    0.43
    Activations Density 1.855%

    No Known Activations