© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13909
    Prev
    Next
    INDEX
    Explanations

    commas, and the words "that", "what", "when", "as", "but", "she" and "and"

    oai_token-act-pair · gemini-2.0-flash

    unusual words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     them
    -1.67
     She
    -1.30
    them
    -1.28
     her
    -1.15
    She
    -1.13
     henne
    -1.10
     herself
    -1.05
     They
    -0.97
    Она
    -0.95
     eux
    -0.94
    POSITIVE LOGITS
    AddTagHelper
    0.51
    Démographie
    0.46
    Ран
    0.45
    hasMoreElements
    0.42
     betweenstory
    0.42
    RegressionTest
    0.42
    UrlResolution
    0.41
     katkı
    0.41
     tarto
    0.40
     mentiras
    0.40
    Activations Density 8.373%

    No Known Activations