© 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. 7372
    Prev
    Next
    INDEX
    Explanations

    words related to programming in multiple languages

    oai_token-act-pair · gemini-2.0-flash

    terms related to coding or programming functions

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

    code snippets and foreign languages

    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
     would
    -2.20
    would
    -1.83
     Would
    -1.62
    Would
    -1.53
     WOULD
    -1.52
     wouldn
    -1.38
     бы
    -1.29
    wouldn
    -1.17
     zou
    -1.12
     sería
    -1.09
    POSITIVE LOGITS
    sizeCache
    0.83
     Majefty
    0.82
    mybatisplus
    0.81
     pleaſure
    0.79
     houſe
    0.78
     MainAxisSize
    0.78
     uſe
    0.75
    abetes
    0.75
     صوتيه
    0.74
     ſte
    0.74
    Activations Density 0.280%

    No Known Activations