© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11726
    Prev
    Next
    INDEX
    Explanations

    descriptions of something in the process of changing into something else

    oai_token-act-pair · gemini-2.0-flash

    turn, turning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Faça
    -0.47
    raphe
    -0.45
     accesso
    -0.45
     vainqueur
    -0.44
    entry
    -0.44
    MemoryWarning
    -0.43
    Compute
    -0.43
    echos
    -0.42
    Concepts
    -0.42
    ambilan
    -0.41
    POSITIVE LOGITS
     turned
    1.59
     turn
    1.55
     become
    1.48
     turning
    1.47
     turns
    1.46
     transform
    1.45
     converted
    1.44
     transformed
    1.43
     convert
    1.43
     becomes
    1.43
    Activations Density 1.374%

    No Known Activations