© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3290
    Prev
    Next
    INDEX
    Explanations

    descriptions of flowers, leaves, and plant parts

    oai_token-act-pair · gemini-2.0-flash

    flowers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ArgsConstructor
    -0.66
    BeginInit
    -0.61
    SequentialGroup
    -0.59
    Rooms
    -0.54
     Meksiku
    -0.47
     kaarangay
    -0.47
    dolu
    -0.46
    roppo
    -0.46
     Rooms
    -0.46
    seeking
    -0.45
    POSITIVE LOGITS
    ंदीखरीदारी
    0.68
    AlterField
    0.64
    MemoryWarning
    0.57
     rowspan
    0.56
     JpaRepository
    0.52
    parsedMessage
    0.52
    tisgarh
    0.52
     Majefty
    0.51
    粗
    0.51
    zerland
    0.50
    Activations Density 4.664%

    No Known Activations