© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 135
    Prev
    Next
    INDEX
    Explanations

    words that describe the progression or transition between states or events, the actions of humans and things, and medical or psychological states.

    oai_token-act-pair · gemini-2.0-flash

    beginnings or changes

    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
     linking
    -0.80
     connecting
    -0.71
     covering
    -0.68
     Targeting
    -0.65
     marking
    -0.65
     Covering
    -0.63
     supporting
    -0.63
     tracking
    -0.63
     answering
    -0.62
     targeting
    -0.60
    POSITIVE LOGITS
     changing
    1.00
     Changing
    0.91
     increasing
    0.82
    Running
    0.81
     Running
    0.79
    changing
    0.79
     growing
    0.78
     evolving
    0.78
    Changing
    0.77
     Growing
    0.77
    Activations Density 7.654%

    No Known Activations