© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1908
    Prev
    Next
    INDEX
    Explanations

    words that describe the status of a situation, thing, or argument as changing or progressing over time.

    oai_token-act-pair · gemini-2.0-flash

    actions progressing over time

    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
    <bos>
    -0.75
     Réponses
    -0.63
     دیکھیے
    -0.50
    intellij
    -0.47
     svým
    -0.46
     endforeach
    -0.45
    images
    -0.45
     تعدى
    -0.45
    Hozzáférés
    -0.44
    zędu
    -0.44
    POSITIVE LOGITS
    CloseOperation
    0.75
    下载附件
    0.59
     AllMovie
    0.56
     محفوظة
    0.55
    Filmografie
    0.52
    ]--;
    0.50
    !("{
    0.50
     ammi
    0.50
    hmig
    0.50
     thrown
    0.49
    Activations Density 11.721%

    No Known Activations