© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4598
    Prev
    Next
    INDEX
    Explanations

    text related to water and drainage

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     water
    -1.36
    water
    -1.18
     Water
    -1.18
    Water
    -1.16
     WATER
    -1.05
    WATER
    -0.99
    水
    -0.92
     agua
    -0.91
     água
    -0.90
     Wasser
    -0.86
    POSITIVE LOGITS
    脚注の使い方
    0.88
    ChildScrollView
    0.74
     محفوظة
    0.73
     ligiloj
    0.72
    migrationBuilder
    0.72
    httphttps
    0.72
     BoxDecoration
    0.71
    AnchorStyles
    0.70
    <%@
    0.69
    BagConstraints
    0.69
    Activations Density 3.181%

    No Known Activations