© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11479
    Prev
    Next
    INDEX
    Explanations

    somewhat idiomatic phrases with articles and prepositions that could be considered financial in any way.

    oai_token-act-pair · gemini-2.0-flash

    references to pockets and wallets

    np_token-act-pair-logits · gpt-4o-mini

    money and finance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     سكانية
    -0.66
     мәкал
    -0.61
     незавершена
    -0.56
    ataires
    -0.55
     '\\;'
    -0.54
    Sucesor
    -0.54
    Rohy
    -0.53
    EDEFAULT
    -0.53
    vician
    -0.52
     nahilalakip
    -0.52
    POSITIVE LOGITS
     pocket
    1.88
     pockets
    1.73
     wallet
    1.72
     Pocket
    1.56
     purse
    1.53
    pocket
    1.52
     wallets
    1.51
     Pockets
    1.47
    Pocket
    1.44
     Wallet
    1.34
    Activations Density 1.072%

    No Known Activations