© 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. 13191
    Prev
    Next
    INDEX
    Explanations

    code snippets related to event timers and registries

    oai_token-act-pair · gemini-2.0-flash

    register timer

    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
    GraphicsUnit
    -0.61
    matchCondition
    -0.60
     Audiodateien
    -0.60
    tagHelperRunner
    -0.57
    AnchorStyles
    -0.56
    Notae
    -0.52
     Else
    -0.52
    Посилання
    -0.51
    enumi
    -0.51
    ://$
    -0.51
    POSITIVE LOGITS
    وصلات
    0.53
     समीक्षाएं
    0.51
    WaitGroup
    0.48
    OrNil
    0.48
    tinyos
    0.47
    )))));
    0.46
     autorytatywna
    0.46
     дописавши
    0.45
     ProtoMessage
    0.45
    Carriera
    0.44
    Activations Density 1.425%

    No Known Activations