© 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. 9826
    Prev
    Next
    INDEX
    Explanations

    words related to contests and getting involved in organizations

    oai_token-act-pair · gemini-2.0-flash

    administrative terms and descriptors

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

    events, sales, and promotions

    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
    -0.94
     дописавши
    -0.74
    脚注の使い方
    -0.74
     الرياضيه
    -0.68
    ArrowToggle
    -0.66
    Referències
    -0.65
    CodedInputStream
    -0.65
    UIControlState
    -0.62
     الحره
    -0.62
    RTGC
    -0.62
    POSITIVE LOGITS
     is
    0.49
     normaux
    0.49
     tecnici
    0.47
     meille
    0.46
     privados
    0.45
     must
    0.45
     gjø
    0.45
     igenom
    0.45
     poveznice
    0.45
     vastaan
    0.44
    Activations Density 2.166%

    No Known Activations