© 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. 11868
    Prev
    Next
    INDEX
    Explanations

    words and phrases that relate to the same idea being repeated in different areas, including code, chemistry, politics, family history or Mormonism

    oai_token-act-pair · gemini-2.0-flash

    Repetition

    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
    pane
    -0.47
     denselben
    -0.46
    CloseOperation
    -0.45
    adaptiveStyles
    -0.45
    lju
    -0.45
     miej
    -0.44
     canali
    -0.44
     Spisak
    -0.41
     StringTokenizer
    -0.41
    çük
    -0.41
    POSITIVE LOGITS
     EClass
    0.65
    FailureListener
    0.63
    complexType
    0.63
    }))
    0.62
    SpringBootTest
    0.59
     للمعارف
    0.57
     INVENTION
    0.57
    ysacchar
    0.57
    ,‎
    0.56
    raeli
    0.56
    Activations Density 51.922%

    No Known Activations