© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10753
    Prev
    Next
    INDEX
    Explanations

    conversational text with personal pronouns and modal verbs, possibly related to recommendations

    oai_token-act-pair · gemini-2.0-flash

    spending money

    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
    Gemeinden
    -0.56
    KommentareTeilen
    -0.52
    ReusableCell
    -0.48
    
    -0.48
     bordada
    -0.48
     moneys
    -0.47
     money
    -0.47
    money
    -0.47
     jabón
    -0.47
     pagare
    -0.46
    POSITIVE LOGITS
     spend
    2.39
     spent
    2.30
     spending
    2.17
     spends
    2.16
     Spend
    2.14
     Spent
    2.02
    Spend
    2.02
    spent
    1.98
    spend
    1.97
     Spending
    1.95
    Activations Density 8.901%

    No Known Activations