© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14272
    Prev
    Next
    INDEX
    Explanations

    the word "water" in various contexts

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    -1.24
    water
    -1.11
     Water
    -1.09
    Water
    -1.05
    WATER
    -0.98
     WATER
    -0.97
    水
    -0.84
     água
    -0.77
     waters
    -0.77
     agua
    -0.69
    POSITIVE LOGITS
    enumii
    0.59
    Jereo
    0.57
    DropTable
    0.57
    sidemargin
    0.53
     Normdatei
    0.52
     BoxDecoration
    0.52
     hauts
    0.50
     Wallflower
    0.50
    XmlEnum
    0.50
    floors
    0.49
    Activations Density 6.144%

    No Known Activations