© 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. 14207
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" followed by a verb, and references to people being discussed.

    oai_token-act-pair · gemini-2.0-flash

    words that begin with specific characters or patterns

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

    go

    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
     itſelf
    -1.00
     myſelf
    -0.94
     Houſe
    -0.94
     Efq
    -0.87
     Majefty
    -0.87
     ſeveral
    -0.85
     Reſ
    -0.84
     houſe
    -0.83
    ſelf
    -0.82
     themſelves
    -0.81
    POSITIVE LOGITS
     u
    0.46
    ಳ
    0.41
    żesz
    0.40
     Wicidata
    0.38
    ilead
    0.38
    stock
    0.36
     sü
    0.36
    はじめに
    0.35
     schien
    0.35
    tock
    0.34
    Activations Density 1.699%

    No Known Activations