© 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. 1944
    Prev
    Next
    INDEX
    Explanations

    LaTeX markup and equations

    oai_token-act-pair · gemini-2.0-flash

    special characters in document formatting

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

    \

    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
     ThemeData
    -0.62
    +:+
    -0.55
     views
    -0.53
    äischen
    -0.50
     Tyr
    -0.48
    DoubleQuotes
    -0.47
     Iglesia
    -0.47
     priesthood
    -0.47
     critics
    -0.46
     scoreless
    -0.46
    POSITIVE LOGITS
     متحده
    0.68
     betweenstory
    0.60
     bezeichneter
    0.59
     GenerationType
    0.58
    IntoConstraints
    0.57
     disambiguazione
    0.57
    Hochspringen
    0.56
    NewUrlParser
    0.55
     HasFactory
    0.54
    Vidite
    0.54
    Activations Density 0.983%

    No Known Activations