© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11447
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly Java and possibly other languages, along with some related terms.

    oai_token-act-pair · gemini-2.0-flash

    varied text sources

    np_max-act-logits · gemini-2.0-flash

    (

    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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     copii
    -0.57
     Dumnezeu
    -0.55
    DockStyle
    -0.54
     îna
    -0.52
     Vedi
    -0.52
    MessageOf
    -0.50
    EndInit
    -0.50
     Ră
    -0.49
     barbati
    -0.49
     nimic
    -0.48
    POSITIVE LOGITS
    IFORNIA
    0.61
    ISTICAL
    0.57
    ilingual
    0.52
    IENTE
    0.50
    ITARY
    0.50
     setImage
    0.48
    tabak
    0.48
    FECTION
    0.48
    học
    0.48
    Straße
    0.48
    Activations Density 8.580%

    No Known Activations