© 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. 2493
    Prev
    Next
    INDEX
    Explanations

    the fragments 'du', 'gri', 'legiti', 'recti' or 'lo'

    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
     оригіналу
    -0.73
    webElementXpaths
    -0.68
    GraphicsUnit
    -0.66
     NSCoder
    -0.66
     initComponents
    -0.65
    currentColor
    -0.63
    ImageContext
    -0.62
    principalColumn
    -0.61
    WithIOException
    -0.60
    tagHelperRunner
    -0.58
    POSITIVE LOGITS
    ssus
    0.52
     án
    0.50
    mijn
    0.50
    sitis
    0.48
    ίνει
    0.47
    alisis
    0.44
    ainville
    0.44
    iseksi
    0.42
     eventdata
    0.42
    alysis
    0.42
    Activations Density 0.129%

    No Known Activations