© 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. 2845
    Prev
    Next
    INDEX
    Explanations

    words relating to people, companies, and groups

    oai_token-act-pair · gemini-2.0-flash

    words indicating size (big/large)

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

    large size

    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
     GenerationType
    -0.57
    ConstraintMaker
    -0.54
    GeneratedMessage
    -0.54
     Matka
    -0.49
    agrama
    -0.49
    argout
    -0.49
    жели
    -0.48
    riedenheit
    -0.48
     Pythagoras
    -0.48
     carc
    -0.47
    POSITIVE LOGITS
     big
    1.94
     large
    1.74
    big
    1.70
    large
    1.55
     Large
    1.29
    Large
    1.29
     LARGE
    1.24
     BIG
    1.23
    Big
    1.21
     Big
    1.20
    Activations Density 1.284%

    No Known Activations