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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6428
    Prev
    Next
    INDEX
    Explanations

    the word "for" in the context of prices or deals, possibly also other prepositions like "at", "on", and "in" in similar contexts

    oai_token-act-pair · gemini-2.0-flash

    mentions of pricing or financial transactions

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

    commerce

    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
     EconPapers
    -0.71
    省市镇
    -0.63
     ErrIntOverflow
    -0.60
     ffilmiau
    -0.60
     <>",
    -0.60
    MigrationBuilder
    -0.59
     '\\;'
    -0.59
    RectangleBorder
    -0.56
    Datuak
    -0.56
    setVerticalGroup
    -0.54
    POSITIVE LOGITS
     under
    0.48
    ]--;
    0.48
    UNDER
    0.47
     $.
    0.47
    featureID
    0.45
    érico
    0.45
    ViewFeatures
    0.44
     remp
    0.43
    dika
    0.43
    थि
    0.42
    Activations Density 0.975%

    No Known Activations