© 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. 13768
    Prev
    Next
    INDEX
    Explanations

    language related to technical sales and convincing customers of a product's value.

    oai_token-act-pair · 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
     enfans
    -0.93
     âmes
    -0.89
     prisonniers
    -0.87
     preuves
    -0.81
     Juifs
    -0.80
     réfugiés
    -0.78
     chrétiens
    -0.78
     vérit
    -0.77
     ouvriers
    -0.77
     bénéfices
    -0.77
    POSITIVE LOGITS
    saraba
    0.59
    ########.
    0.53
     cherchés
    0.48
    Suara
    0.43
     mo
    0.42
     okuyayım
    0.42
     CURIAM
    0.41
    andExpect
    0.41
    BASEPATH
    0.41
     cards
    0.40
    Activations Density 3.425%

    No Known Activations