© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13918
    Prev
    Next
    INDEX
    Explanations

    the prefix "Amb" typically found at the beginning of product names

    oai_token-act-pair · gemini-2.0-flash

    Amb/Emb

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Tē
    -0.52
    XmlAccessType
    -0.51
    CreateTable
    -0.50
    losure
    -0.49
    KURZBESCHREIBUNG
    -0.49
    endregion
    -0.49
    emate
    -0.48
    emf
    -0.47
    principalColumn
    -0.47
    ooga
    -0.46
    POSITIVE LOGITS
    TintMode
    0.71
     للاسماء
    0.69
     sumpay
    0.63
    ⓘ
    0.62
     Cár
    0.60
    ագրություններ
    0.59
     Monfieur
    0.59
     TimeUnit
    0.59
    MessageTagHelper
    0.57
     doubtnut
    0.57
    Activations Density 0.278%

    No Known Activations