© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15856
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are related to a time when someone is transitioning from one state to another and words indicative of lists

    oai_token-act-pair · gemini-2.0-flash

    something ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Reading
    -0.76
    Reading
    -0.73
     reading
    -0.71
     Monitoring
    -0.69
     monitoring
    -0.69
     READING
    -0.67
    reading
    -0.66
     Playing
    -0.66
    Monitoring
    -0.65
     Sensing
    -0.63
    POSITIVE LOGITS
     becoming
    0.99
     closing
    0.98
     ending
    0.96
     disappearing
    0.92
     opening
    0.89
     turning
    0.87
     arriving
    0.87
     retiring
    0.86
     returning
    0.85
     graduating
    0.85
    Activations Density 14.510%

    No Known Activations