© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12488
    Prev
    Next
    INDEX
    Explanations

    mostly finds equal signs, number prefixes, png file extensions, and other seemingly random ascii strings

    oai_token-act-pair · gemini-2.0-flash

    png

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Theſe
    -0.71
     */;
    -0.71
     myſelf
    -0.69
    
    -0.66
     greateſt
    -0.66
    脚注の使い方
    -0.65
     Monfieur
    -0.64
     Escolar
    -0.62
     BoxFit
    -0.62
    StoryboardSegue
    -0.61
    POSITIVE LOGITS
    <bos>
    0.84
    queryInterface
    0.58
     }{@
    0.48
    Демографія
    0.46
    BeginContext
    0.44
    TypedDataSet
    0.44
     vọng
    0.44
    SequentialGroup
    0.44
    altezza
    0.43
    ratory
    0.42
    Activations Density 5.927%

    No Known Activations