© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 16002
    Prev
    Next
    INDEX
    Explanations

    words related to experience, time, and sequence of events, particularly in personal stories.

    oai_token-act-pair · gemini-2.0-flash

    short story excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     reafon
    -0.78
     yourselves
    -0.75
     houſe
    -0.74
     ddelweddau
    -0.73
     perfons
    -0.72
     Shakspeare
    -0.71
     Houſe
    -0.71
    RenderAtEndOf
    -0.71
     foon
    -0.71
     Chriftian
    -0.71
    POSITIVE LOGITS
     we
    0.68
     one
    0.55
     my
    0.47
    弊
    0.46
    nocache
    0.42
     kami
    0.42
     egyik
    0.42
     another
    0.42
    layoutControl
    0.41
     trong
    0.40
    Activations Density 1.864%

    No Known Activations