© 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. 13843
    Prev
    Next
    INDEX
    Explanations

    sentences that describe scientific research and its limitations

    oai_token-act-pair · gemini-2.0-flash

    small/insufficient

    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
    المناصب
    -0.71
     esternos
    -0.68
    Personensuche
    -0.61
     Wiktionnaire
    -0.58
    ]='\
    -0.57
     sessionFactory
    -0.56
     AttributeSet
    -0.56
    脚注の使い方
    -0.55
     iprot
    -0.54
     مواليد
    -0.52
    POSITIVE LOGITS
     meager
    1.11
     tiny
    1.11
     limited
    1.08
     sparse
    1.03
     weak
    1.02
     poor
    1.00
    limited
    1.00
     meagre
    0.99
    Poor
    0.95
     feeble
    0.95
    Activations Density 2.425%

    No Known Activations