© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10949
    Prev
    Next
    INDEX
    Explanations

    words related to experimentation, preproduction or copying something.

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
     replicate
    -2.14
     Copy
    -2.08
     copy
    -2.08
     replication
    -2.05
     replicated
    -1.99
     copying
    -1.98
    Copy
    -1.95
     duplicate
    -1.95
     copied
    -1.94
     replicates
    -1.94
    POSITIVE LOGITS
    возь
    0.41
     ко
    0.35
     rø
    0.35
     Schwe
    0.35
    ğim
    0.35
     Florence
    0.34
     Firenze
    0.33
    Surface
    0.33
     fizer
    0.33
    sient
    0.32
    Activations Density 2.504%

    No Known Activations