© 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. 11431
    Prev
    Next
    INDEX
    Explanations

    code and programming related symbols (particularly "Mvx" and "IMvx")

    oai_token-act-pair · gemini-2.0-flash

    Code and errors

    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
    tisgarh
    -0.49
    MM
    -0.48
    fieldLabel
    -0.45
    MLLoader
    -0.45
     stanovnika
    -0.44
    BackStack
    -0.43
    MR
    -0.41
    am
    -0.40
    openConnection
    -0.40
     pescoço
    -0.39
    POSITIVE LOGITS
     surla
    0.68
    AccessorTable
    0.65
     initWithFrame
    0.65
     Efq
    0.62
     Dux
    0.62
    |}{$
    0.61
    ruptedException
    0.59
     Broom
    0.58
     viewDidLoad
    0.57
    jsonwebtoken
    0.57
    Activations Density 0.760%

    No Known Activations