© 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. 11209
    Prev
    Next
    INDEX
    Explanations

    many different things, but it has a stronger affinity for extracting questions from text, especially from online forums.

    oai_token-act-pair · gemini-2.0-flash

    Code/technical 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_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
    saraba
    -0.52
    breos
    -0.47
     cho
    -0.43
    hin
    -0.42
    αλ
    -0.42
    CppMethod
    -0.42
    JsonFormat
    -0.41
    BASEPATH
    -0.41
    /*"
    -0.40
    cipy
    -0.40
    POSITIVE LOGITS
    <eos>
    0.93
    AndEndTag
    0.86
    InjectAttribute
    0.83
    0.77
    LikeLiked
    0.69
     AssemblyCulture
    0.68
    Encyklopedia
    0.68
     оригіналу
    0.66
     avoient
    0.66
     dAtA
    0.65
    Activations Density 6.423%

    No Known Activations