© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11623
    Prev
    Next
    INDEX
    Explanations

    proper nouns that specify a location or organization

    oai_token-act-pair · gemini-2.0-flash

    Street and location reporting

    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
     nationaux
    -0.55
     nationales
    -0.53
    iteracy
    -0.49
     okuyayım
    -0.47
     national
    -0.47
    Predecesor
    -0.47
     urbaine
    -0.47
     applau
    -0.46
    national
    -0.46
    역사
    -0.45
    POSITIVE LOGITS
     EClass
    0.71
     createSlice
    0.68
     محفوظة
    0.67
     الاطلاع
    0.63
     betweenstory
    0.60
    titleMargin
    0.59
     mergeFrom
    0.58
    NOPQRST
    0.58
     تعدى
    0.58
    Vidite
    0.57
    Activations Density 6.301%

    No Known Activations