© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13698
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation

    oai_token-act-pair · gemini-2.0-flash

    mathematical and code notations

    np_max-act-logits · gemini-2.0-flash

    say "closing brackets"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     hogyan
    -0.57
    andExpect
    -0.55
     lentement
    -0.46
     Barbour
    -0.46
    かわらず
    -0.46
     khúc
    -0.45
     publicitaires
    -0.44
     marins
    -0.44
     publiques
    -0.43
     élas
    -0.43
    POSITIVE LOGITS
    OGND
    0.66
     Wicidata
    0.63
    BufferException
    0.60
    IContainer
    0.59
     GenerationType
    0.59
    RTLR
    0.59
     geslacht
    0.59
    MemoryWarning
    0.58
     препратки
    0.57
    ritch
    0.56
    Activations Density 3.208%

    No Known Activations