© 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. 11893
    Prev
    Next
    INDEX
    Explanations

    technical documents about mechanical devices and machines

    oai_token-act-pair · gemini-2.0-flash

    Buying, manufacturing, repairing machines

    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
    雯
    -0.50
    cedentes
    -0.49
    damente
    -0.46
     fournies
    -0.45
     alta
    -0.45
    eria
    -0.44
    alais
    -0.43
    och
    -0.43
     fó
    -0.43
    chot
    -0.43
    POSITIVE LOGITS
     resourceCulture
    0.87
     houſe
    0.84
     '\\;'
    0.78
     Cæsar
    0.78
     itſelf
    0.76
     ſta
    0.76
    BufferException
    0.75
     diagonals
    0.75
     ſte
    0.73
     flutes
    0.73
    Activations Density 11.434%

    No Known Activations