© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4680
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms and phrases

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    \{\\
    -0.72
     ModelExpression
    -0.72
    UnusedPrivate
    -0.65
     оригіналу
    -0.61
     snippetHide
    -0.61
    SpringBootTest
    -0.61
    Aholisi
    -0.61
    mybatisplus
    -0.60
    ModelSerializer
    -0.59
    สึก
    -0.57
    POSITIVE LOGITS
     purposes
    1.14
     purpose
    0.91
    purposes
    0.88
     Purposes
    0.86
     for
    0.84
     For
    0.84
    Purpose
    0.74
    For
    0.74
    purpose
    0.72
     Purpose
    0.69
    Activations Density 1.623%

    No Known Activations