© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11223
    Prev
    Next
    INDEX
    Explanations

    words within the context of baseball teams and locations

    oai_token-act-pair · gemini-2.0-flash

    Locations, people, events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    adaptiveStyles
    -0.71
    onAttach
    -0.63
    GEBURTSDATUM
    -0.54
    KURZBESCHREIBUNG
    -0.52
    __(/*!
    -0.52
     gepubliceerd
    -0.52
    significant
    -0.51
    relativeTime
    -0.51
    pulumi
    -0.50
     allAfrica
    -0.50
    POSITIVE LOGITS
     للمعارف
    0.66
    اشة
    0.53
     préfé
    0.49
    wię
    0.47
    TAG
    0.46
     aérienne
    0.46
    komendasi
    0.45
    rensa
    0.45
    Berikut
    0.45
     éti
    0.45
    Activations Density 1.943%

    No Known Activations