© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12068
    Prev
    Next
    INDEX
    Explanations

    mentions of past events and actions

    oai_token-act-pair · gemini-2.0-flash

    was/were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    TintMode
    -0.76
     Мексичка
    -0.69
    )];
    -0.62
     Шта
    -0.59
    PreferredItem
    -0.59
     "..\..\
    -0.57
    rxjs
    -0.56
    WebElementEntity
    -0.56
     ujednoznacz
    -0.55
     _$
    -0.54
    POSITIVE LOGITS
    NewUrlParser
    0.60
    classnames
    0.51
     esternos
    0.51
     AUSSI
    0.50
    ArgsConstructor
    0.50
     grünen
    0.50
     Vedi
    0.49
    EFAULT
    0.49
    🟩
    0.48
     green
    0.47
    Activations Density 8.638%

    No Known Activations