© 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. 8635
    Prev
    Next
    INDEX
    Explanations

    numbers and words often found in the titles of creative works

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'ul'

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

    Code/log data

    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
    abestanden
    -0.78
    Билгалдахарш
    -0.74
    Erreferentziak
    -0.74
     الحره
    -0.73
    AddTagHelper
    -0.72
     unknownFields
    -0.71
     للمعارف
    -0.71
    Искәрмәләр
    -0.68
     CreateTagHelper
    -0.68
    IsContent
    -0.67
    POSITIVE LOGITS
    ul
    0.87
    UL
    0.56
    lul
    0.52
    rul
    0.52
    uls
    0.52
    oul
    0.50
    ulz
    0.48
    oterapia
    0.48
    bred
    0.46
    ornata
    0.44
    Activations Density 0.899%

    No Known Activations