© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11985
    Prev
    Next
    INDEX
    Explanations

    code and formal writing constructs such as citations, applications, research grants, and file paths

    oai_token-act-pair · gemini-2.0-flash

    technical/academic documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    mybatisplus
    -0.69
    CloseOperation
    -0.68
     الحره
    -0.64
    ftagPool
    -0.62
     виправивши
    -0.60
    Portail
    -0.59
    енча
    -0.58
     незавершена
    -0.58
     оригіналу
    -0.56
    Hozzáférés
    -0.54
    POSITIVE LOGITS
     nakalista
    0.65
    ElementException
    0.60
    tagez
    0.58
    endregion
    0.56
     copertina
    0.55
    ModelAndView
    0.55
     uLocal
    0.54
    有何
    0.53
    Handlung
    0.52
    asjons
    0.52
    Activations Density 3.538%

    No Known Activations