© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8712
    Prev
    Next
    INDEX
    Explanations

    legal language related to wills, estates, trusts, trustees, and beneficiaries

    oai_token-act-pair · gemini-2.0-flash

    administration-related terms

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

    Trusts and estates

    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
     виправивши
    -0.79
    DoubleQuotes
    -0.74
     ransom
    -0.62
     autorytatywna
    -0.61
    ISupport
    -0.60
    ніципалі
    -0.58
    antiation
    -0.56
    たまた
    -0.56
    rzost
    -0.56
     defStyleAttr
    -0.56
    POSITIVE LOGITS
     administration
    0.68
    +:+
    0.61
     Letters
    0.60
    administration
    0.58
     LETTERS
    0.55
     Administration
    0.55
    Prob
    0.54
     ADMINISTRATION
    0.54
     prob
    0.53
    Letters
    0.53
    Activations Density 1.938%

    No Known Activations