© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14485
    Prev
    Next
    INDEX
    Explanations

    HTML code related to navigation bars and plus/minus symbols (likely related to expandable content)

    oai_token-act-pair · gemini-2.0-flash

    Site UI elements

    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
     hand
    -0.46
     GetEnumerator
    -0.44
     pointed
    -0.43
    kirchen
    -0.43
     propres
    -0.42
    padek
    -0.41
     palmas
    -0.41
     her
    -0.41
     internationaux
    -0.41
    reactstrap
    -0.40
    POSITIVE LOGITS
    AndEndTag
    0.77
     AssemblyCulture
    0.71
    __(/*!
    0.68
    didSet
    0.66
    ỏi
    0.64
     AttributeSet
    0.63
    crollView
    0.63
     gild
    0.63
    ILabel
    0.62
    /**
    0.61
    Activations Density 0.736%

    No Known Activations