© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10214
    Prev
    Next
    INDEX
    Explanations

    text related to legal agreements, terms of use, and privacy policies

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to programming or coding

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

    say "terms privacy user policy"

    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
    adau
    -0.47
     bestand
    -0.46
    BufferedImage
    -0.46
     INTERESAR
    -0.46
     برانيه
    -0.46
     izquierdo
    -0.44
     constat
    -0.44
    issance
    -0.43
    ein
    -0.43
    richtungen
    -0.42
    POSITIVE LOGITS
    SourceChecksum
    0.73
    windowFixed
    0.64
    drawSprites
    0.60
     MainAxisSize
    0.60
    Geplaatst
    0.59
    bitField
    0.59
     lenker
    0.58
    protoc
    0.57
    setVerticalGroup
    0.56
    AsUp
    0.56
    Activations Density 1.160%

    No Known Activations