© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9158
    Prev
    Next
    INDEX
    Explanations

    the presence of numbers and delimiters

    oai_token-act-pair · gemini-2.0-flash

    specific character patterns and sports-related terminology

    np_token-act-pair-logits · gpt-4o-mini

    Numerical/reference data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Roskov
    -0.88
    IntoConstraints
    -0.72
    Autoritní
    -0.71
     Вікі
    -0.69
    قایناق‌لار
    -0.68
    SharedCtor
    -0.66
    ніципалі
    -0.63
    IUrlHelper
    -0.63
    DoubleQuotes
    -0.63
     nahilalakip
    -0.63
    POSITIVE LOGITS
     
    1.45
    1
    0.63
     ۱
    0.50
     ১
    0.49
    SupportActionBar
    0.46
    JsonNode
    0.45
    2
    0.45
     XNUMX
    0.45
    stood
    0.44
    idenav
    0.44
    Activations Density 1.798%

    No Known Activations