© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10575
    Prev
    Next
    INDEX
    Explanations

    scientific text likely about evolution with a large amount of words that are common English auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    evolution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     evolution
    -2.06
     evolve
    -1.94
    Evolution
    -1.93
     Evolution
    -1.88
     evolved
    -1.87
    evolution
    -1.86
     EVOLUTION
    -1.78
     evolutionary
    -1.75
     evolu
    -1.70
     evolves
    -1.66
    POSITIVE LOGITS
    buttonBar
    0.49
    titleMargin
    0.44
     kö
    0.44
     judiciales
    0.43
    ]._
    0.42
    plier
    0.42
     ко
    0.41
    LG
    0.41
    mitteln
    0.41
     ICC
    0.41
    Activations Density 2.319%

    No Known Activations