© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13094
    Prev
    Next
    INDEX
    Explanations

    words related to genetics, taxonomy, and species evolution

    oai_token-act-pair · gemini-2.0-flash

    World

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    RegistryLite
    -0.65
    LayoutStyle
    -0.63
     EconPapers
    -0.59
    gypti
    -0.55
    runApp
    -0.54
    +:+
    -0.54
    ernalia
    -0.53
    NUMX
    -0.52
    Kaieteur
    -0.51
    يكب
    -0.51
    POSITIVE LOGITS
    Captor
    0.50
    PyErr
    0.49
    bootstrapcdn
    0.48
    ột
    0.47
    bcryptjs
    0.46
    findpost
    0.45
    PyExc
    0.44
     couvert
    0.44
     Chol
    0.43
     moderni
    0.43
    Activations Density 1.390%

    No Known Activations