© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2211
    Prev
    Next
    INDEX
    Explanations

    dates within text and some keywords such as railway station, but generally has a low confidence

    oai_token-act-pair · gemini-2.0-flash

    Events being or been

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     early
    -0.96
    Early
    -0.92
    early
    -0.90
     Early
    -0.84
     EARLY
    -0.78
    EARLY
    -0.76
    早期
    -0.65
     earlier
    -0.63
    早
    -0.62
     sooner
    -0.58
    POSITIVE LOGITS
    IntoConstraints
    0.69
    mybatisplus
    0.68
    UnitTesting
    0.64
     myſelf
    0.63
     vuitton
    0.63
    mpotent
    0.62
    openConnection
    0.61
     ་་
    0.61
     الحره
    0.61
    ➟
    0.60
    Activations Density 27.090%

    No Known Activations