© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3584
    Prev
    Next
    INDEX
    Explanations

    text related to making choices and their consequences in life

    oai_token-act-pair · gemini-2.0-flash

    life and personal struggles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     longevity
    -0.73
     people
    -0.73
     mind
    -0.68
     minds
    -0.68
     thinking
    -0.66
     being
    -0.66
    think
    -0.65
     conscience
    -0.65
     complexity
    -0.64
    being
    -0.64
    POSITIVE LOGITS
    plotly
    0.49
    pptx
    0.47
    DockStyle
    0.47
     reprinted
    0.46
     pinned
    0.46
     hosted
    0.46
     مترجم
    0.45
     previo
    0.44
     penned
    0.43
    PositiveButton
    0.43
    Activations Density 5.931%

    No Known Activations