© 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. 14506
    Prev
    Next
    INDEX
    Explanations

    product dimensions and shipping information

    oai_token-act-pair · gemini-2.0-flash

    Capitalized abbreviations/acronyms

    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
     оригіналу
    -0.75
     صوتيه
    -0.74
    WithIOException
    -0.71
    eaways
    -0.69
     poffe
    -0.67
    Carriera
    -0.67
     Monfieur
    -0.66
     purpoſe
    -0.65
    RegressionTest
    -0.65
     AssemblyCulture
    -0.65
    POSITIVE LOGITS
     H
    0.59
     Net
    0.52
     Total
    0.49
     net
    0.46
     Base
    0.45
     L
    0.45
     Front
    0.45
     Wide
    0.45
     app
    0.44
     Stage
    0.44
    Activations Density 17.478%

    No Known Activations