© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2787
    Prev
    Next
    INDEX
    Explanations

    question words and related punctuation

    oai_token-act-pair · gemini-2.0-flash

    "What's [something]"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     ſmall
    -0.81
     JpaRepository
    -0.78
     pleaſure
    -0.76
     purpoſe
    -0.76
     <>",
    -0.76
     itſelf
    -0.76
    ſelf
    -0.73
    OrBuilder
    -0.72
     متعلقه
    -0.71
     reaſon
    -0.71
    POSITIVE LOGITS
     wrong
    0.58
     up
    0.55
     new
    0.53
     qu
    0.52
    UP
    0.47
    wrong
    0.46
     become
    0.46
    qu
    0.46
     Qu
    0.44
    new
    0.44
    Activations Density 0.648%

    No Known Activations