© 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. 7795
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    oai_token-act-pair · gemini-2.0-flash

    coding or mathematical notation

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

    Latex/Math notation

    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
    screw
    -0.36
    strokeColor
    -0.35
     broadest
    -0.35
    ÂN
    -0.35
    obstacle
    -0.34
     llama
    -0.34
     gyhoeddwyd
    -0.34
    Screw
    -0.33
     gained
    -0.33
    łada
    -0.33
    POSITIVE LOGITS
    ftagPool
    0.83
     BoxFit
    0.81
    +#+#
    0.78
     تضيفلها
    0.74
     vPvB
    0.73
     الرياضيه
    0.72
    abstractmethod
    0.71
    rrggbb
    0.70
    EndContext
    0.69
    enderror
    0.68
    Activations Density 1.041%

    No Known Activations