© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 97
    Prev
    Next
    INDEX
    Explanations

    words related to wrestling teams and wrestlers

    oai_token-act-pair · gemini-2.0-flash

    sophomore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     students
    -0.90
     student
    -0.86
    Students
    -0.84
     Students
    -0.82
    students
    -0.78
    student
    -0.73
     STUDENTS
    -0.73
     studenten
    -0.72
    Student
    -0.72
     Student
    -0.72
    POSITIVE LOGITS
     AssemblyCulture
    0.66
    DockStyle
    0.66
    OGND
    0.63
    ंदीखरीदारी
    0.59
    Enllaces
    0.58
    <bos>
    0.56
     ligiloj
    0.54
    brtc
    0.54
     gabbana
    0.54
     Audiodateien
    0.54
    Activations Density 0.323%

    No Known Activations