© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10816
    Prev
    Next
    INDEX
    Explanations

    a variety of substrings including partial words and numbers

    oai_token-act-pair · gemini-2.0-flash

    program code and foreign text

    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
    er
    -2.81
    ER
    -1.57
    erà
    -1.43
    erate
    -1.40
    erl
    -1.28
    erii
    -1.26
    erti
    -1.13
    erai
    -1.09
    erli
    -1.07
    erus
    -1.05
    POSITIVE LOGITS
     degradability
    0.57
    RenderAtEndOf
    0.54
     Améli
    0.53
     Biôgrafia
    0.49
    __":
    0.49
    hoid
    0.48
    ゴリー
    0.48
    WriteTagHelper
    0.47
    AccessorTable
    0.47
     fuf
    0.46
    Activations Density 2.552%

    No Known Activations