© 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. 2048
    Prev
    Next
    INDEX
    Explanations

    programming code and database terminology

    oai_token-act-pair · gemini-2.0-flash

    programming 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_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
    état
    -1.16
     state
    -1.16
    STATE
    -1.10
     état
    -1.10
    state
    -1.08
     État
    -1.07
     STATE
    -1.06
     ftate
    -1.02
    State
    -1.02
     State
    -1.01
    POSITIVE LOGITS
     Han
    0.43
     han
    0.42
     new
    0.42
    束
    0.39
     tra
    0.39
    ,
    0.39
     str
    0.38
    .
    0.38
     по
    0.37
    py
    0.37
    Activations Density 0.685%

    No Known Activations