© 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. 12669
    Prev
    Next
    INDEX
    Explanations

    words in sports-related stories that describe people, places, and actions in a high degree

    oai_token-act-pair · gemini-2.0-flash

    terms related to coaching

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

    coaches

    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
    tagHelperRunner
    -0.71
     للمعارف
    -0.63
     }{@
    -0.61
    LLocation
    -0.60
    GeoNames
    -0.58
     féd
    -0.57
     esternos
    -0.57
    AutoScaleMode
    -0.57
     nvm
    -0.55
     autoridad
    -0.54
    POSITIVE LOGITS
     coaches
    0.57
     Coaches
    0.54
    Salut
    0.52
    Coaching
    0.52
    Coaches
    0.51
    ={({
    0.51
     coach
    0.51
     school
    0.48
     cle
    0.47
    LookAnd
    0.47
    Activations Density 1.625%

    No Known Activations