© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16079
    Prev
    Next
    INDEX
    Explanations

    the words "push," "try," and words related to notifications and communication code

    oai_token-act-pair · gemini-2.0-flash

    push

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     push
    -2.98
     Push
    -2.94
    Push
    -2.77
     pushed
    -2.72
     PUSH
    -2.67
     pushes
    -2.66
    push
    -2.64
     pushing
    -2.64
     Pushing
    -2.58
    Pushing
    -2.45
    POSITIVE LOGITS
    ScopeManager
    0.67
    MLLoader
    0.56
    最快更新
    0.54
    StandardCharsets
    0.53
    teness
    0.52
    EndContext
    0.52
    TAGS
    0.51
    NgModule
    0.51
     IPX
    0.49
    TypedDataSet
    0.49
    Activations Density 1.306%

    No Known Activations