© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9119
    Prev
    Next
    INDEX
    Explanations

    words frequently found in scientific research papers concerning the benefits of information distribution and how to get "access to" things

    oai_token-act-pair · gemini-2.0-flash

    words indicating access barriers

    np_token-act-pair-logits · gpt-4o-mini

    access to services/opportunities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     disambiguazione
    -0.72
    toHave
    -0.62
    tagHelperRunner
    -0.60
    ValueStyle
    -0.57
    
    -0.55
    IonicModule
    -0.54
     للاسماء
    -0.52
    ">//
    -0.52
     ویکی‌پدیای
    -0.50
    
    -0.48
    POSITIVE LOGITS
     ddelweddau
    0.55
     obscure
    0.52
     lại
    0.52
    EDEFAULT
    0.52
     specific
    0.51
     narrowly
    0.50
    modb
    0.50
    AddWithValue
    0.49
    כז
    0.49
    ？
    0.48
    Activations Density 4.476%

    No Known Activations