© 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. 5090
    Prev
    Next
    INDEX
    Explanations

    names in a sports historical documents

    oai_token-act-pair · gemini-2.0-flash

    peak

    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
     Arthur
    -0.72
    GraphicsUnit
    -0.71
    Arthur
    -0.70
     ARTHUR
    -0.67
     Larry
    -0.66
     Frank
    -0.65
    Harold
    -0.65
     Fred
    -0.65
     Harold
    -0.63
     Bill
    -0.63
    POSITIVE LOGITS
     peak
    1.92
    Peak
    1.85
    peak
    1.81
     Peak
    1.80
     peaks
    1.67
     PEAK
    1.53
    peaks
    1.39
     Peaks
    1.38
     peaking
    1.31
     peaked
    1.30
    Activations Density 3.367%

    No Known Activations