© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9531
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ed' or the substring 'if'

    oai_token-act-pair · gemini-2.0-flash

    rib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     propOrder
    -0.61
     arşivlendi
    -0.52
     Avo
    -0.52
     kaynağından
    -0.52
    losigkeit
    -0.50
     szóci
    -0.50
    ьаж
    -0.49
    styleUrls
    -0.49
     Whales
    -0.48
     avo
    -0.48
    POSITIVE LOGITS
     administrations
    0.76
     distribution
    0.73
     distributing
    0.71
     distributes
    0.69
     administration
    0.69
     administering
    0.68
    distribution
    0.66
     Administration
    0.65
     Distribution
    0.65
    DISTRIBUTION
    0.65
    Activations Density 0.471%

    No Known Activations