© 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. 5631
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing something being true or in a state of being

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    getting
    -0.96
     becoming
    -0.96
     growing
    -0.90
    going
    -0.88
    becoming
    -0.88
     Becoming
    -0.87
    growing
    -0.86
     Growing
    -0.85
     getting
    -0.84
     Getting
    -0.83
    POSITIVE LOGITS
     chré
    0.63
     incluyendo
    0.56
    ASHI
    0.50
     henvis
    0.50
     vœux
    0.49
     oídos
    0.49
    fört
    0.49
     vestiti
    0.49
     bakom
    0.49
     samfun
    0.49
    Activations Density 6.395%

    No Known Activations