© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8772
    Prev
    Next
    INDEX
    Explanations

    geological and geographical terms related to the ocean and/or Iceland

    oai_token-act-pair · gemini-2.0-flash

    Tectonic plates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    RenderAtEndOf
    -0.73
     calendriers
    -0.69
     Signalez
    -0.65
    UnsafeEnabled
    -0.64
    FormTagHelper
    -0.62
    EDEFAULT
    -0.61
    setVerticalGroup
    -0.61
    Filmographie
    -0.60
    rawQuery
    -0.59
    ">//
    -0.59
    POSITIVE LOGITS
     plate
    0.84
     plates
    0.79
     Plates
    0.73
     Plate
    0.73
    plate
    0.68
    plates
    0.66
    Plates
    0.66
     PLATES
    0.65
    Plate
    0.65
    プレート
    0.59
    Activations Density 1.039%

    No Known Activations