© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1100
    Prev
    Next
    INDEX
    Explanations

    personal pronouns, auxiliary verbs, and question words

    oai_token-act-pair · gemini-2.0-flash

    "put"

    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
    tagHelperRunner
    -0.93
     مشين
    -0.92
     snippetHide
    -0.83
    parsedMessage
    -0.77
     consultato
    -0.75
    oredCriteria
    -0.75
     initComponents
    -0.75
    ollectionView
    -0.73
    Hentet
    -0.71
    RTDA
    -0.70
    POSITIVE LOGITS
     put
    0.80
    put
    0.68
     placement
    0.63
    Put
    0.63
     Put
    0.62
     placing
    0.60
     putting
    0.58
    Putting
    0.58
     placed
    0.57
     Putting
    0.55
    Activations Density 2.762%

    No Known Activations