© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1524
    Prev
    Next
    INDEX
    Explanations

    references to published scientific literature, including journal names, volume numbers, issue numbers, page numbers, and publication years

    oai_token-act-pair · gemini-2.0-flash

    scientific publications

    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
    олові
    -0.64
    cheinend
    -0.60
    Autoritní
    -0.58
    ContentAsync
    -0.54
     Insee
    -0.53
    EndProject
    -0.52
     solas
    -0.52
     ISP
    -0.52
     incomplète
    -0.51
     shootout
    -0.51
    POSITIVE LOGITS
    DatabaseError
    0.52
     invokingState
    0.50
     controlling
    0.50
     Audiodateien
    0.47
     initComponents
    0.46
    pozycji
    0.46
    staticmethod
    0.46
     AutoMapper
    0.45
    makeConstraints
    0.44
    ense
    0.44
    Activations Density 9.820%

    No Known Activations