© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11121
    Prev
    Next
    INDEX
    Explanations

    punctuation and words related to insurance and legal advice

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     AssemblyCulture
    -0.76
     >=",
    -0.66
     defaultstate
    -0.61
    elemField
    -0.59
    الإنجليزية
    -0.55
    contentLoaded
    -0.52
    bootstrapcdn
    -0.52
     препратки
    -0.52
    Personendaten
    -0.51
    Datuak
    -0.50
    POSITIVE LOGITS
     Careful
    0.78
     Remember
    0.77
     Watch
    0.73
     Beware
    0.69
    Watch
    0.66
     particulières
    0.64
    Remember
    0.63
     ricorda
    0.63
     Consider
    0.63
     Be
    0.63
    Activations Density 0.878%

    No Known Activations