© 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. 11437
    Prev
    Next
    INDEX
    Explanations

    words related to medical issues, motherhood, and the challenges of life

    oai_token-act-pair · gemini-2.0-flash

    challenges and difficulties

    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
    msgTypes
    -0.51
    ’?
    -0.50
    esgue
    -0.49
    uxxxx
    -0.49
    )?
    -0.43
    ’
    -0.43
    ”?
    -0.42
    ElementType
    -0.40
    Datuak
    -0.40
     book
    -0.39
    POSITIVE LOGITS
    EndContext
    0.73
    Scénario
    0.66
    writeFieldEnd
    0.63
     المعيارى
    0.63
     contextLoads
    0.62
     tématu
    0.61
    rophes
    0.59
    édrale
    0.59
     JAXBElement
    0.58
    bored
    0.58
    Activations Density 1.647%

    No Known Activations