© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3399
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, specifically exponents and subscripts

    oai_token-act-pair · gemini-2.0-flash

    LaTeX math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    SharedCtor
    -0.62
    RegistryLite
    -0.56
    RenderAtEndOf
    -0.54
    SerializedSize
    -0.50
    featureID
    -0.47
    XMLSchema
    -0.46
    artifactId
    -0.44
    providedIn
    -0.44
    fjspx
    -0.42
    urlpatterns
    -0.42
    POSITIVE LOGITS
     Efq
    0.76
     Houſe
    0.63
     houſe
    0.60
     Mika
    0.60
     touchpad
    0.59
     auffi
    0.58
     itſelf
    0.58
     greateſt
    0.57
    Shack
    0.57
     Anſ
    0.56
    Activations Density 0.336%

    No Known Activations