© 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. 2542
    Prev
    Next
    INDEX
    Explanations

    dates and times, and prepositions relating to them

    oai_token-act-pair · gemini-2.0-flash

    time/dates

    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
     late
    -3.33
    Late
    -3.20
     Late
    -3.14
    late
    -2.91
     LATE
    -2.86
    Early
    -2.77
     Early
    -2.72
     early
    -2.69
    early
    -2.66
    LATE
    -2.52
    POSITIVE LOGITS
     Paglinawan
    0.71
    Бахар
    0.63
    AccessException
    0.56
    bufio
    0.54
    itology
    0.52
    issons
    0.51
     CWE
    0.51
     onOptions
    0.50
    XmlAccessorType
    0.49
     Familienname
    0.48
    Activations Density 3.224%

    No Known Activations