© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12793
    Prev
    Next
    INDEX
    Explanations

    the word "supra" and words like "method" and "reach"

    oai_token-act-pair · gemini-2.0-flash

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.12
    ↵↵
    -0.64
     The
    -0.63
     
    -0.60
     I
    -0.59
    ’
    -0.56
     the
    -0.54
     A
    -0.54
    .
    -0.53
     &
    -0.52
    POSITIVE LOGITS
    MessageTagHelper
    0.73
    FXML
    0.72
    ########.
    0.70
    XmlAccessorType
    0.69
     Diretto
    0.68
     EEU
    0.68
    StoreMessageInfo
    0.67
     SCSI
    0.66
     RDC
    0.66
     Riproduzione
    0.66
    Activations Density 1.221%

    No Known Activations