© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13027
    Prev
    Next
    INDEX
    Explanations

    the phrase "play a [positive adjective] role"

    oai_token-act-pair · gemini-2.0-flash

    Central importance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    MLLoader
    -0.71
    μως
    -0.48
     Lives
    -0.48
    bootstrapcdn
    -0.47
     LIVES
    -0.46
    Chúng
    -0.45
    HasMaxLength
    -0.45
    Église
    -0.45
    SerializedSize
    -0.45
    Remarque
    -0.44
    POSITIVE LOGITS
    rungsseite
    0.64
     sectarian
    0.57
    avadoc
    0.57
    UrlResolution
    0.56
    EUROPA
    0.55
    sizeCache
    0.52
     cohomology
    0.52
     Mockito
    0.52
     فريبيس
    0.51
     wireType
    0.50
    Activations Density 1.689%

    No Known Activations