© 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. 11748
    Prev
    Next
    INDEX
    Explanations

    names and place names with accented characters

    oai_token-act-pair · gemini-2.0-flash

    scraped web content

    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
    참고
    -0.75
     Houſe
    -0.75
     itſelf
    -0.74
    ########.
    -0.73
    EndInit
    -0.73
     occaf
    -0.71
    offsetof
    -0.70
     Amiens
    -0.69
    Referencies
    -0.69
     ſtate
    -0.68
    POSITIVE LOGITS
     kasarigan
    0.43
     الحره
    0.38
    GEBURTS
    0.36
     المعيارى
    0.36
     personnelles
    0.34
    ابراین
    0.33
    tonode
    0.31
    MessageTagHelper
    0.31
     nhiêu
    0.30
     culturelles
    0.30
    Activations Density 0.284%

    No Known Activations