© 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. 4513
    Prev
    Next
    INDEX
    Explanations

    text related to property tax and trusts

    oai_token-act-pair · gemini-2.0-flash

    terms related to property and taxation

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

    tax avoidance

    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
     disambiguazione
    -0.82
     فريبيس
    -0.78
    ंदीखरीदारी
    -0.76
    posedge
    -0.76
    Билгалдахарш
    -0.76
     للمعارف
    -0.72
    iastes
    -0.71
     snippetHide
    -0.68
    enumii
    -0.68
     myſelf
    -0.68
    POSITIVE LOGITS
     Chain
    0.56
     chain
    0.55
    Chain
    0.54
    chain
    0.49
    Stamp
    0.47
    orton
    0.46
     CHAIN
    0.44
    ERVIS
    0.44
     h
    0.44
     Stamp
    0.43
    Activations Density 1.008%

    No Known Activations