© 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. 12724
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to limits, particularly minimums

    oai_token-act-pair · gemini-2.0-flash

    terms and phrases related to minimum or baseline requirements

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

    minimum

    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
    ValueStyle
    -0.90
    Tembelea
    -0.86
     kasarigan
    -0.82
     Roskov
    -0.82
     насељу
    -0.80
    ftagPool
    -0.78
     AssemblyProduct
    -0.77
    UnitTesting
    -0.75
     poveznice
    -0.73
     jspb
    -0.70
    POSITIVE LOGITS
    bles
    0.49
     risk
    0.49
    rement
    0.48
     recommendation
    0.47
     performance
    0.47
    ífica
    0.44
     loss
    0.44
     interface
    0.44
     Sol
    0.44
    RowCount
    0.44
    Activations Density 7.480%

    No Known Activations