© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3821
    Prev
    Next
    INDEX
    Explanations

    colons

    oai_token-act-pair · gemini-2.0-flash

    Colon punctuation

    np_max-act · gemini-2.0-flash

    :

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.34
    ↵↵
    -1.00
     
    -0.97
    ,
    -0.94
    '
    -0.93
    ’
    -0.80
    .
    -0.80
     in
    -0.79
    ↵
    -0.79
     to
    -0.75
    POSITIVE LOGITS
     betweenstory
    2.27
    WithIOException
    2.16
    GEBURTSDATUM
    2.13
    RegressionTest
    2.11
    ьаж
    1.99
    IndentedString
    1.95
     propOrder
    1.95
    DockStyle
    1.95
     CreateTagHelper
    1.91
     disambiguazione
    1.89
    Activations Density 1.406%

    No Known Activations