© 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. 14583
    Prev
    Next
    INDEX
    Explanations

    code snippets from various programming languages with a focus on angular

    oai_token-act-pair · gemini-2.0-flash

    low-frequency or uncommon words with special characters

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

    Code/web elements

    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
     N
    -0.52
     A
    -0.50
     i
    -0.49
     
    -0.49
     hu
    -0.49
     B
    -0.48
     As
    -0.48
     em
    -0.48
     «
    -0.47
     T
    -0.46
    POSITIVE LOGITS
     moschino
    0.97
     ſever
    0.96
     Majefty
    0.93
     preſent
    0.93
     Monfieur
    0.93
     Houſe
    0.92
     Anſ
    0.92
     doubtnut
    0.91
     Diſ
    0.90
     houſe
    0.88
    Activations Density 2.589%

    No Known Activations