© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12506
    Prev
    Next
    INDEX
    Explanations

    sentences that describe a body of water

    oai_token-act-pair · gemini-2.0-flash

    bodies of 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Spring
    -0.79
    Spring
    -0.79
     spring
    -0.79
     SPRING
    -0.75
    spring
    -0.73
    SPRING
    -0.73
    springs
    -0.68
     sprung
    -0.63
    ChromeDriver
    -0.62
     springs
    -0.57
    POSITIVE LOGITS
    MigrationBuilder
    0.78
     AssemblyCulture
    0.56
     pertes
    0.54
     head
    0.53
    dymyr
    0.52
     meridian
    0.50
     jouet
    0.50
    andescent
    0.50
    ptonshire
    0.49
    السكان
    0.49
    Activations Density 2.070%

    No Known Activations