© 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. 15048
    Prev
    Next
    INDEX
    Explanations

    source code and documentation-related tokens, possibly including weather information

    oai_token-act-pair · gemini-2.0-flash

    unusual tokens or terms

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

    Technical specifications and components

    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
     Theſe
    -0.71
     Efq
    -0.71
     Италијани
    -0.67
     photolibrary
    -0.66
     Monfieur
    -0.65
     raiſ
    -0.64
     bandai
    -0.63
     moschino
    -0.62
     myſelf
    -0.62
    IsMutable
    -0.61
    POSITIVE LOGITS
    terase
    0.60
     للمعارف
    0.54
     оригіналу
    0.54
     Ho
    0.52
    Geplaatst
    0.50
     Mar
    0.50
    
    0.50
    isDirectory
    0.49
     Pro
    0.49
    GEBURTSDATUM
    0.49
    Activations Density 0.393%

    No Known Activations