© 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. 10382
    Prev
    Next
    INDEX
    Explanations

    words related to chemicals or fertilizers being applied in powder and liquid form

    oai_token-act-pair · gemini-2.0-flash

    Powders and liquids

    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
     insuffisamment
    -0.45
     поряд
    -0.41
    AutoresizingMask
    -0.40
     luck
    -0.40
     CURIAM
    -0.40
    swamp
    -0.39
     prisão
    -0.38
     CreateTagHelper
    -0.38
    otri
    -0.38
    lovakia
    -0.38
    POSITIVE LOGITS
    IMPORTED
    0.85
    AccessorTable
    0.82
     Chriftian
    0.80
     Diſ
    0.79
    (!__
    0.78
     ſeveral
    0.75
     Houſe
    0.74
     Theſe
    0.74
     Jefus
    0.72
     Reſ
    0.72
    Activations Density 1.439%

    No Known Activations