© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6183
    Prev
    Next
    INDEX
    Explanations

    the phrase "came from" (or similar)

    oai_token-act-pair · gemini-2.0-flash

    say "from"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    comes
    -1.35
     comes
    -1.34
     Comes
    -1.33
     coming
    -1.32
     COMES
    -1.29
     come
    -1.27
     Coming
    -1.26
    come
    -1.25
    coming
    -1.24
    Coming
    -1.21
    POSITIVE LOGITS
     from
    1.38
    จาก
    0.85
     från
    0.82
     dari
    0.82
     desde
    0.82
    from
    0.79
     từ
    0.77
     от
    0.75
     FROM
    0.73
     از
    0.64
    Activations Density 0.745%

    No Known Activations