© 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. 9916
    Prev
    Next
    INDEX
    Explanations

    words and values related to time in the context of computer related things like an auto renewal

    oai_token-act-pair · gemini-2.0-flash

    this

    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
     Lower
    -0.56
    Lower
    -0.52
     lower
    -0.50
    modelBuilder
    -0.48
    idalgo
    -0.48
    utched
    -0.46
    DropColumn
    -0.45
     Methuen
    -0.45
    ρώ
    -0.44
    ()?;
    -0.44
    POSITIVE LOGITS
     protoimpl
    0.71
    AddTagHelper
    0.71
     للمعارف
    0.70
    CodeAttribute
    0.69
    djangoproject
    0.68
    BufferException
    0.64
     Réponses
    0.64
    CompleteListener
    0.57
    bitField
    0.57
     kaarangay
    0.56
    Activations Density 1.919%

    No Known Activations