© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1395
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and medical vocabulary used in constitutional law and virology

    oai_token-act-pair · gemini-2.0-flash

    legal/scientific documents

    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
     pro
    -1.09
     Pro
    -1.00
    Pro
    -0.90
    pro
    -0.89
     con
    -0.79
     PRO
    -0.69
    PRO
    -0.66
    プロ
    -0.63
     sup
    -0.63
     provid
    -0.57
    POSITIVE LOGITS
     Audiodateien
    0.84
     beau
    0.75
    ंदीखरीदारी
    0.74
    setVerticalGroup
    0.71
    migrationBuilder
    0.71
     ivelany
    0.69
    expandindo
    0.67
    tagext
    0.66
     differ
    0.65
     rela
    0.63
    Activations Density 17.143%

    No Known Activations