© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6136
    Prev
    Next
    INDEX
    Explanations

    text describing role-playing video games

    oai_token-act-pair · gemini-2.0-flash

    the word "Turn"

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

    video games

    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
     للاسماء
    -0.96
     الحره
    -0.84
    tagHelperRunner
    -0.81
     AssemblyCompany
    -0.71
    ViewImports
    -0.71
    IUrlHelper
    -0.66
    ंदीखरीदारी
    -0.66
     resourceCulture
    -0.66
    isContained
    -0.66
     שוליים
    -0.65
    POSITIVE LOGITS
     turn
    0.50
     dis
    0.47
     Turn
    0.46
     fifth
    0.45
    nesty
    0.45
     third
    0.41
     differential
    0.41
    gico
    0.40
     Dis
    0.40
    Turn
    0.40
    Activations Density 0.959%

    No Known Activations