© 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. 11491
    Prev
    Next
    INDEX
    Explanations

    tokens that appear after the period character, especially in code

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     betweenstory
    -1.15
    featureID
    -0.93
    MessageOf
    -0.85
    rrggbb
    -0.84
    rungsseite
    -0.82
     Wikimedijinoj
    -0.81
    liferay
    -0.81
     AssemblyTitle
    -0.79
     становника
    -0.75
     nahilalakip
    -0.74
    POSITIVE LOGITS
    ometric
    0.46
     Again
    0.44
    ersdorf
    0.43
    Again
    0.42
    elp
    0.42
     firm
    0.40
    τια
    0.39
     again
    0.39
     lo
    0.39
    рованию
    0.39
    Activations Density 0.728%

    No Known Activations