© 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. 8244
    Prev
    Next
    INDEX
    Explanations

    words and phrases that seem to be related to the setup, configuration, and use of Linux or Ubuntu

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    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
     being
    -1.12
     doing
    -1.05
     getting
    -1.03
     taking
    -1.02
     making
    -0.98
     finding
    -0.98
     obtaining
    -0.96
     creating
    -0.96
     putting
    -0.94
     managing
    -0.94
    POSITIVE LOGITS
    ^(@)
    0.56
     Offered
    0.53
     potře
    0.53
     femininas
    0.52
     condamné
    0.52
     bisogno
    0.51
     sfida
    0.51
     abbia
    0.50
     käyt
    0.49
     chiesto
    0.49
    Activations Density 0.593%

    No Known Activations