© 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. 9520
    Prev
    Next
    INDEX
    Explanations

    words related to personal anecdotes, especially about parenting and daily routines.

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terms

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

    code or foreign words

    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
     againſt
    -0.83
     becauſe
    -0.79
     Diſ
    -0.77
     poffible
    -0.75
     Reſ
    -0.75
     Theſe
    -0.74
     whoſe
    -0.73
     ſtre
    -0.72
     ſtate
    -0.72
     Monfieur
    -0.72
    POSITIVE LOGITS
    verwijspagina
    0.52
    webElementXpaths
    0.50
    webElementGuid
    0.50
     schle
    0.50
     initComponents
    0.49
    xis
    0.47
     tan
    0.46
     pro
    0.46
    twimg
    0.46
    ModelAdmin
    0.46
    Activations Density 3.954%

    No Known Activations