© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4031
    Prev
    Next
    INDEX
    Explanations

    words used when the writer is talking about the recent past in an informal style

    oai_token-act-pair · gemini-2.0-flash

    terms related to duration

    np_token-act-pair-logits · gpt-4o-mini

    long time periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RenderAtEndOf
    -0.80
    endpush
    -0.66
     فريبيس
    -0.64
    ########.
    -0.62
     estekak
    -0.58
    IndentedString
    -0.57
    RegressionTest
    -0.57
    OGND
    -0.57
    TestingModule
    -0.57
    ChildScrollView
    -0.56
    POSITIVE LOGITS
     forever
    1.76
    forever
    1.50
     FOREVER
    1.41
     ages
    1.33
     Forever
    1.29
    Forever
    1.16
     eternally
    1.10
     Ages
    0.96
     eternity
    0.94
    Ages
    0.91
    Activations Density 1.555%

    No Known Activations