© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14791
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate reflection and evaluation

    oai_token-act-pair · gemini-2.0-flash

    possibilities, opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    oprecipitation
    -0.68
     swimsuit
    -0.65
     TextAppearance
    -0.65
     الرياضيه
    -0.64
    tonsoft
    -0.62
     tabernacle
    -0.60
     SearchView
    -0.60
     sarees
    -0.60
     ChromeDriver
    -0.60
    लिए
    -0.59
    POSITIVE LOGITS
    mockito
    0.49
    GraphicsUnit
    0.47
    pyplot
    0.47
     Dados
    0.45
    żd
    0.44
    readObject
    0.44
     Schatz
    0.44
    LLocation
    0.44
     Realität
    0.44
    ClCompile
    0.43
    Activations Density 2.635%

    No Known Activations