© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3990
    Prev
    Next
    INDEX
    Explanations

    phrases containing adverbs modifying a verb

    oai_token-act-pair · gemini-2.0-flash

    almost

    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
    AndEndTag
    -0.78
    MENAFN
    -0.71
    Hochspringen
    -0.62
    BoxShadow
    -0.62
    windowFixed
    -0.60
     MenuView
    -0.57
    saraba
    -0.57
     quelconque
    -0.57
    shadowOffset
    -0.57
    theless
    -0.56
    POSITIVE LOGITS
     nearly
    1.20
    nearly
    1.03
     almost
    0.99
     Nearly
    0.93
    almost
    0.83
    Nearly
    0.78
     virtually
    0.77
     Almost
    0.72
     hampir
    0.68
    Almost
    0.67
    Activations Density 18.457%

    No Known Activations