© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2792
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and derivatives

    oai_token-act-pair · gemini-2.0-flash

    derivative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Roskov
    -0.82
     igång
    -0.77
    #+#
    -0.77
     publiques
    -0.75
     vectoriales
    -0.75
     spectateurs
    -0.73
    adpleegd
    -0.71
     précip
    -0.69
     decorativas
    -0.69
     japones
    -0.68
    POSITIVE LOGITS
    word
    0.42
    GEBURTSDATUM
    0.40
    GeoNames
    0.39
     Ov
    0.39
     word
    0.39
    旨
    0.38
    派
    0.38
    CODES
    0.37
    ieten
    0.37
     offer
    0.37
    Activations Density 19.109%

    No Known Activations