© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1114
    Prev
    Next
    INDEX
    Explanations

    parts of programming code related to instances of a method being called from another method

    oai_token-act-pair · gemini-2.0-flash

    coding functions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    DeleteBehavior
    -0.73
     Shakspeare
    -0.69
     Chriftian
    -0.67
     Majefty
    -0.65
     intptr
    -0.64
     Jefus
    -0.64
    StoreMessageInfo
    -0.64
     comets
    -0.64
     Italijanski
    -0.64
     dandy
    -0.64
    POSITIVE LOGITS
     n
    0.54
     Kor
    0.52
     g
    0.52
     nakalista
    0.51
     ex
    0.49
     u
    0.49
     am
    0.49
     mutual
    0.49
     mer
    0.48
    lese
    0.48
    Activations Density 0.714%

    No Known Activations