© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7656
    Prev
    Next
    INDEX
    Explanations

    the phrase "the course of" and similar phrasing

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     متعلقه
    -0.75
    الإنجليزية
    -0.65
    ToAction
    -0.57
    ;++
    -0.50
     autorytatywna
    -0.50
     AssemblyCompany
    -0.49
    DockStyle
    -0.49
    interopRequire
    -0.49
    </thead>
    -0.49
    implements
    -0.48
    POSITIVE LOGITS
     course
    3.45
    course
    2.84
     Course
    2.67
     COURSE
    2.61
    Course
    2.59
    COURSE
    2.23
     courses
    2.19
     Courses
    1.91
    courses
    1.91
    Courses
    1.83
    Activations Density 3.408%

    No Known Activations