© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11491
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to film reviews, analysis, and parodies

    oai_token-act-pair · gemini-2.0-flash

    parody

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    yordu
    -0.52
     محفوظة
    -0.52
    ROUTINE
    -0.52
    abstractmethod
    -0.51
    انجليز
    -0.47
    ISupport
    -0.45
    צת
    -0.42
     disponibilités
    -0.41
     releasing
    -0.41
     tĩnh
    -0.40
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
     înc
    0.58
    لاعات
    0.58
    TypedDataSet
    0.58
    chism
    0.58
     shallo
    0.57
     Summa
    0.57
     OnInit
    0.56
     mergeFrom
    0.56
     sherds
    0.55
    Activations Density 0.380%

    No Known Activations