© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6104
    Prev
    Next
    INDEX
    Explanations

    legal discussion of a boat's engine speed and related warranty

    oai_token-act-pair · gemini-2.0-flash

    Mercury

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ContentAsync
    -0.60
     kvar
    -0.50
     recognises
    -0.49
     recognising
    -0.49
     betweenstory
    -0.48
    tgz
    -0.47
    TokenNameRPAREN
    -0.47
     تضيفلها
    -0.46
     recognizes
    -0.45
     dAtA
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.71
    +#+#
    0.60
     surla
    0.54
    Референце
    0.54
    TagMode
    0.53
     inversa
    0.48
    Thrust
    0.48
    MenuInflater
    0.47
     Kean
    0.47
     Domin
    0.46
    Activations Density 1.008%

    No Known Activations