© 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. 10279
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to speculation, judgement, and assessment

    oai_token-act-pair · gemini-2.0-flash

    Seeking feedback

    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>
    -0.96
     africain
    -0.75
     pertanto
    -0.67
     gdyż
    -0.65
     digitais
    -0.61
     asiatique
    -0.61
     charité
    -0.59
     közül
    -0.59
     numai
    -0.58
     culoare
    -0.58
    POSITIVE LOGITS
    epres
    0.70
    viewDidLoad
    0.65
    çalves
    0.64
    ยว
    0.63
    τιά
    0.61
    abancı
    0.60
    ########.
    0.59
    ENARIO
    0.58
    indrops
    0.58
    hidupan
    0.58
    Activations Density 0.526%

    No Known Activations