© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 947
    Prev
    Next
    INDEX
    Explanations

    code snippets, in particular those containing the word 'tuple' and/or testing frameworks like BOOST

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    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
     sé
    -0.31
     zal
    -0.30
    automated
    -0.29
    acquisition
    -0.29
    consensus
    -0.28
     dop
    -0.28
     kap
    -0.28
     tira
    -0.28
    infrastructure
    -0.28
    regulatory
    -0.28
    POSITIVE LOGITS
     Efq
    1.18
     Monfieur
    1.08
     Majefty
    1.08
     Houſe
    1.06
     myſelf
    1.05
     ―――――
    1.05
    ſelf
    1.04
     Jefus
    1.01
    neſs
    1.00
    ſelves
    0.98
    Activations Density 7.868%

    No Known Activations