© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13029
    Prev
    Next
    INDEX
    Explanations

    LaTeX code, especially lengths specified in 'pt'

    oai_token-act-pair · gemini-2.0-flash

    pt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -1.05
    principalTable
    -0.51
    RenderAtEndOf
    -0.48
    '
    -0.48
     AssemblyTitle
    -0.48
     вікі
    -0.46
    findpost
    -0.45
    $('#
    -0.44
    ’
    -0.44
     spot
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.83
     saites
    0.78
    ReusableCell
    0.69
    Przypisy
    0.69
    TestingModule
    0.68
     bağlantılar
    0.65
    timewa
    0.65
    zzleHttp
    0.64
     NDEBUG
    0.63
    typeorm
    0.62
    Activations Density 5.058%

    No Known Activations