© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6153
    Prev
    Next
    INDEX
    Explanations

    code snippets with elements from multiple coding languages, including Javascript ("TypeError") but also Portuguese ("você")

    oai_token-act-pair · gemini-2.0-flash

    Non-English language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     themselves
    -0.72
     are
    -0.59
     were
    -0.58
     their
    -0.56
    themselves
    -0.55
    Their
    -0.49
     będą
    -0.47
    their
    -0.47
     weren
    -0.45
     Their
    -0.45
    POSITIVE LOGITS
    SharedCtor
    0.62
     المعيارى
    0.60
    numerusform
    0.60
     ModelExpression
    0.59
     ivelany
    0.59
     configureStore
    0.58
     EconPapers
    0.57
     Does
    0.57
    uxxxx
    0.57
    aye
    0.56
    Activations Density 0.533%

    No Known Activations