© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10758
    Prev
    Next
    INDEX
    Explanations

    geographical locations along with associated distances or sizes

    oai_token-act-pair · gemini-2.0-flash

    units of distance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ApiException
    -0.54
    AccessorTable
    -0.51
     Distances
    -0.46
    Gret
    -0.45
     distance
    -0.44
    远
    -0.43
     tá
    -0.43
    intura
    -0.43
     Distance
    -0.42
    Carole
    -0.41
    POSITIVE LOGITS
    titleMargin
    0.60
    downarrow
    0.60
    unately
    0.60
     Вікі
    0.58
    elemField
    0.56
    SOUNDBITE
    0.54
    Javadoc
    0.54
    PerformLayout
    0.52
     برانيه
    0.52
    Datuak
    0.52
    Activations Density 1.066%

    No Known Activations