© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11916
    Prev
    Next
    INDEX
    Explanations

    code snippets in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Chham
    -0.75
     Roskov
    -0.75
    GraphicsUnit
    -0.69
    ніципа
    -0.69
     themſelves
    -0.68
    IZA
    -0.68
     linkovi
    -0.68
     ویکی‌پدی
    -0.67
     raiſ
    -0.67
    Бахар
    -0.67
    POSITIVE LOGITS
    出版年
    0.38
    Obrázky
    0.36
     noDo
    0.36
     propOrder
    0.36
     fós
    0.35
     jadi
    0.34
     izdel
    0.34
     ettei
    0.30
     októ
    0.30
    uni
    0.30
    Activations Density 12.197%

    No Known Activations