© 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. 12978
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate desire

    oai_token-act-pair · gemini-2.0-flash

    requests for help or support

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

    for

    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
     to
    -0.78
     onOptions
    -0.59
    SuppressLint
    -0.52
     lenker
    -0.50
    RUnlock
    -0.47
     yüzden
    -0.47
     gäller
    -0.46
    Pautan
    -0.45
    rrggbb
    -0.44
     aikana
    -0.44
    POSITIVE LOGITS
     assistance
    0.68
     a
    0.67
     help
    0.65
    LookAnd
    0.63
    /***/
    0.62
    }{*}{
    0.60
     anything
    0.58
     something
    0.57
    zö
    0.57
     sources
    0.57
    Activations Density 5.248%

    No Known Activations