© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2553
    Prev
    Next
    INDEX
    Explanations

    math equations and statistical notation

    oai_token-act-pair · gemini-2.0-flash

    distribution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    igation
    -0.48
     Teres
    -0.46
    بوابة
    -0.44
    Gambas
    -0.42
     terecht
    -0.42
    lys
    -0.41
     Alig
    -0.41
     CURLOPT
    -0.41
    ỡng
    -0.41
     Drapeau
    -0.40
    POSITIVE LOGITS
     distribution
    1.43
     distributions
    1.32
     Distribution
    1.21
     distributed
    1.20
    distribution
    1.19
     DISTRIBUTION
    1.15
    Distribution
    1.13
     distribute
    1.12
     Distributions
    1.09
     DISTRIB
    1.06
    Activations Density 5.007%

    No Known Activations