© 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. 7420
    Prev
    Next
    INDEX
    Explanations

    chunks of computer code and programming-related text.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    市镇
    -0.46
     allá
    -0.45
    er
    -0.44
    ️
    -0.43
    ificação
    -0.40
    withstanding
    -0.40
    เช่น
    -0.39
    likely
    -0.38
    zero
    -0.38
    ตัว
    -0.37
    POSITIVE LOGITS
     AssemblyTitle
    0.62
    IANGLES
    0.52
    xg
    0.51
    IVersion
    0.51
    kf
    0.51
    olve
    0.51
    mList
    0.51
    tml
    0.50
    ocument
    0.50
    setopt
    0.50
    Activations Density 26.038%

    No Known Activations