© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 530
    Prev
    Next
    INDEX
    Explanations

    instances where the word 'was' is used in a sports context, possibly indicating a player's state or action

    oai_token-act-pair · gemini-2.0-flash

    sports game summaries

    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
    :]:
    -0.48
    IsMutable
    -0.47
    ViewImports
    -0.47
     CanadaChoose
    -0.46
    ⁡
    -0.45
    mergeFrom
    -0.44
    CodedInputStream
    -0.44
     patch
    -0.41
    Patches
    -0.41
    homonymie
    -0.41
    POSITIVE LOGITS
     fédé
    0.77
     automatiques
    0.71
     économiques
    0.69
     chré
    0.69
     électroniques
    0.68
     destinées
    0.68
    enumi
    0.66
     avoient
    0.66
     vectorielles
    0.65
     nationaux
    0.65
    Activations Density 0.889%

    No Known Activations