© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6647
    Prev
    Next
    INDEX
    Explanations

    code snippets in various programming languages and technical terms related to programming

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

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

    Computer code properties

    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
    ########.
    -1.16
     виправивши
    -1.04
     للمعارف
    -0.75
     tartalomajánló
    -0.70
    MigrationBuilder
    -0.70
    Rohy
    -0.70
    +#+#
    -0.69
    antMatchers
    -0.69
     nahilalakip
    -0.68
     ostavi
    -0.67
    POSITIVE LOGITS
    lossians
    0.44
     put
    0.39
     DNA
    0.38
    sprüng
    0.38
     let
    0.37
     c
    0.37
    wani
    0.35
    期刊论文
    0.35
     rich
    0.35
     bet
    0.35
    Activations Density 1.752%

    No Known Activations