© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5000
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with health, youth, and comparisons

    oai_token-act-pair · gemini-2.0-flash

    statistical likelihood

    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
     likely
    -0.73
    FunctionFlags
    -0.71
    uxxxx
    -0.67
     Likely
    -0.66
    EndContext
    -0.65
    ScopeManager
    -0.64
    likely
    -0.64
    exitRule
    -0.64
    Likely
    -0.62
    Palmarès
    -0.59
    POSITIVE LOGITS
     vues
    0.54
    hesive
    0.52
    Checked
    0.50
    ETCH
    0.48
    stamos
    0.47
     NSCoder
    0.47
    commen
    0.47
    aurait
    0.46
     recognising
    0.46
     sord
    0.46
    Activations Density 11.582%

    No Known Activations