© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3881
    Prev
    Next
    INDEX
    Explanations

    descriptive sections about key characters and plot points in a story.

    oai_token-act-pair · gemini-2.0-flash

    main characters and antagonists

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

    story elements

    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
     ModelExpression
    -0.59
     vectorielle
    -0.50
    MLLoader
    -0.50
     dentaire
    -0.48
     vierge
    -0.45
     élector
    -0.45
    ghalaya
    -0.44
     forgiven
    -0.43
     Severity
    -0.43
     COND
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.75
     antagonist
    0.71
    Tikang
    0.71
     central
    0.64
    ząca
    0.62
     antagonists
    0.61
     &___
    0.60
    mainloop
    0.59
     villain
    0.57
    central
    0.55
    Activations Density 2.301%

    No Known Activations