© 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. 6719
    Prev
    Next
    INDEX
    Explanations

    code syntax in multiple programming languages.

    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
     avoient
    -1.09
     auroit
    -1.07
     dévelo
    -1.06
     pouvoit
    -1.06
     étoient
    -1.04
     feroit
    -1.04
     normaux
    -0.99
     scolaires
    -0.95
     alimentaires
    -0.95
     aveug
    -0.94
    POSITIVE LOGITS
     south
    0.39
     ro
    0.39
     sea
    0.37
     sun
    0.37
    west
    0.35
     air
    0.35
     sky
    0.35
     god
    0.34
     west
    0.34
     ves
    0.34
    Activations Density 1.813%

    No Known Activations