© 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. 10182
    Prev
    Next
    INDEX
    Explanations

    sentences that contain interjections or trailing thoughts denoted by ellipses or other punctuation

    oai_token-act-pair · gemini-2.0-flash

    ellipses

    np_max-act · gemini-2.0-flash
    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>
    -1.20
     nemlig
    -0.42
     przecież
    -0.41
     attiv
    -0.40
     presentazione
    -0.38
    catchError
    -0.37
    Now
    -0.37
     viennent
    -0.37
    Just
    -0.36
     chiuso
    -0.36
    POSITIVE LOGITS
     "..\..\
    0.76
    numerusform
    0.73
     onOptions
    0.67
    inkgo
    0.66
    AxisAlignment
    0.65
    ImageIO
    0.63
    Obrázky
    0.62
     "..\..\..\
    0.62
     thiệu
    0.62
     versa
    0.62
    Activations Density 0.694%

    No Known Activations