© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 16026
    Prev
    Next
    INDEX
    Explanations

    uses of the words "is", "has", "been", "was", "we", or "were" in scientific text.

    oai_token-act-pair · gemini-2.0-flash

    been

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     '\\;'
    -0.75
    rungsseite
    -0.69
     uintptr
    -0.67
     ModelExpression
    -0.66
     GenerationType
    -0.65
     ddelweddau
    -0.65
    aarrggbb
    -0.64
     متعلقه
    -0.63
    HttpDelete
    -0.62
     termica
    -0.62
    POSITIVE LOGITS
     пу
    0.45
     /\.
    0.45
    рова
    0.45
    ứ
    0.44
    "}")
    0.43
     autorytatywna
    0.43
    migrationBuilder
    0.41
     từng
    0.41
     yle
    0.41
    gris
    0.40
    Activations Density 3.955%

    No Known Activations