© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7519
    Prev
    Next
    INDEX
    Explanations

    sentences that include discussion of the timeline of evolution of diatoms or sponges

    oai_token-act-pair · gemini-2.0-flash

    archaeological finds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    thylamine
    -0.51
     Early
    -0.49
     early
    -0.49
    olis
    -0.47
     long
    -0.47
    early
    -0.46
    TagHelper
    -0.46
    ')}}"
    -0.45
     null
    -0.45
    رشف
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.82
    GTCX
    0.66
    ="@+
    0.66
    StructEnd
    0.63
    bootstrapcdn
    0.62
    بوابة
    0.62
    Diweddarwch
    0.61
    +#+#
    0.60
    ToBounds
    0.60
     виправивши
    0.59
    Activations Density 1.486%

    No Known Activations