© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12848
    Prev
    Next
    INDEX
    Explanations

    the word 'thing', but also activates for other words like 'one', 'friend', 'benefits' and 'more'

    oai_token-act-pair · gemini-2.0-flash

    thing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    لاثة
    -0.47
    checkable
    -0.47
     Lel
    -0.46
     deles
    -0.45
    sendKeys
    -0.45
    例
    -0.45
     delas
    -0.45
     Ejemplo
    -0.44
    versi
    -0.44
    Example
    -0.43
    POSITIVE LOGITS
    RegressionTest
    1.01
     disambiguazione
    0.80
    tinyos
    0.75
    <bos>
    0.71
    AddTagHelper
    0.71
     विश्वसनीयता
    0.70
    
    0.69
     ExecuteAsync
    0.68
    )|^{
    0.68
    extAlignment
    0.66
    Activations Density 1.295%

    No Known Activations