© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9560
    Prev
    Next
    INDEX
    Explanations

    mentions of "last" and "minute" (often together) and "first"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "last" and "minute."

    np_token-act-pair-logits · gpt-4o-mini

    last

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    gameserver
    -0.77
    っこう
    -0.71
    providedIn
    -0.55
    Abp
    -0.54
    FunctionFlags
    -0.54
    ẵn
    -0.53
     Tenggara
    -0.52
    reportWebVitals
    -0.52
     EconPapers
    -0.52
    PyExc
    -0.52
    POSITIVE LOGITS
    minute
    0.75
     minute
    0.72
    Minute
    0.69
     moment
    0.68
    MINUTE
    0.60
     Minute
    0.60
     moments
    0.57
    moment
    0.56
    moments
    0.55
     nakalista
    0.54
    Activations Density 0.850%

    No Known Activations