© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13563
    Prev
    Next
    INDEX
    Explanations

    enumerated lists or numbered points

    oai_token-act-pair · gemini-2.0-flash

    1 or a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     faz
    -0.46
     Me
    -0.45
     nu
    -0.43
    ast
    -0.42
    pun
    -0.42
    ொ
    -0.42
    ern
    -0.42
    busch
    -0.42
     labor
    -0.41
    וג
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.72
    tagHelperRunner
    0.69
    ViewImports
    0.69
     ComVisible
    0.67
    цездатний
    0.66
    OGND
    0.65
    GEBURTSDATUM
    0.64
    RenderAtEndOf
    0.63
    HasAnnotation
    0.61
     TextAppearance
    0.60
    Activations Density 0.323%

    No Known Activations