© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7291
    Prev
    Next
    INDEX
    Explanations

    single letters used as variables in code

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    HasAnnotation
    -0.82
     برانيه
    -0.57
    __':
    -0.55
     समीक्षक
    -0.55
    '))
    -0.51
     crossorigin
    -0.50
    Carriera
    -0.49
     utafitiHapana
    -0.48
     CanadaChoose
    -0.48
     Exacts
    -0.47
    POSITIVE LOGITS
    Vidite
    0.59
     initComponents
    0.58
     ſtate
    0.54
     purpoſe
    0.52
     fubject
    0.51
     asunder
    0.51
     Theſe
    0.50
    neſs
    0.49
     Efq
    0.49
    AsUp
    0.48
    Activations Density 1.963%

    No Known Activations