© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 14984
    Prev
    Next
    INDEX
    Explanations

    code with colons

    oai_token-act-pair · gemini-2.0-flash

    colons and parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    <eos>
    -0.47
    nestjs
    -0.46
     distanciation
    -0.43
     complètes
    -0.42
     alcance
    -0.41
    toBe
    -0.40
    ivably
    -0.40
    zerne
    -0.39
    vantages
    -0.38
     adultos
    -0.35
    POSITIVE LOGITS
     مشين
    1.20
     препратки
    0.79
    LookAnd
    0.77
    ImageContext
    0.76
    SourceChecksum
    0.75
     itſelf
    0.75
     MotionEvent
    0.74
    WriteTagHelper
    0.73
    InputBorder
    0.73
    NameInMap
    0.72
    Activations Density 0.962%

    No Known Activations