© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13688
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to resources, advice or assistance

    oai_token-act-pair · gemini-2.0-flash

    Everyone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Datuak
    -0.97
     ModelExpression
    -0.75
    taxia
    -0.73
     pleaſure
    -0.67
     jScrollPane
    -0.63
     reaſon
    -0.61
    PMailer
    -0.61
     reafon
    -0.60
    LEncoder
    -0.60
     propOrder
    -0.59
    POSITIVE LOGITS
     that
    0.63
     everyone
    0.62
     galore
    0.59
    Everyone
    0.55
     chiunque
    0.55
     Everyone
    0.53
     anyone
    0.52
     متعلقه
    0.52
     EVERYONE
    0.52
     everybody
    0.51
    Activations Density 0.723%

    No Known Activations