© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6607
    Prev
    Next
    INDEX
    Explanations

    text describing laboratory procedures in molecular biology

    oai_token-act-pair · gemini-2.0-flash

    water

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     кӀ
    -0.53
     فريبيس
    -0.52
    URIComponent
    -0.43
     paix
    -0.43
    enschappelijke
    -0.42
     hyö
    -0.41
    DateField
    -0.40
     käytt
    -0.40
    ubblica
    -0.38
     timmar
    -0.38
    POSITIVE LOGITS
     water
    1.66
     Water
    1.44
    water
    1.41
    Water
    1.39
     WATER
    1.34
    WATER
    1.28
     agua
    1.07
     Вода
    1.04
     água
    1.03
     Wasser
    1.02
    Activations Density 1.511%

    No Known Activations