© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15226
    Prev
    Next
    INDEX
    Explanations

    technical scientific language, specifically related to theoretical physics

    oai_token-act-pair · gemini-2.0-flash

    quantum physics

    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
     '\\;'
    -0.84
     nakalista
    -0.78
    adaptiveStyles
    -0.76
     الرياضيه
    -0.74
    writeFieldEnd
    -0.72
     useAppContext
    -0.69
    GraphicsUnit
    -0.68
     onPostExecute
    -0.67
    AccessorTable
    -0.67
    parsedMessage
    -0.67
    POSITIVE LOGITS
    B
    0.45
    はじめに
    0.42
    Philosop
    0.41
    buttonStyle
    0.41
    ortunadamente
    0.40
    anguardia
    0.40
    L
    0.40
    X
    0.40
     Zero
    0.40
    こんにちは
    0.39
    Activations Density 2.787%

    No Known Activations