© 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. 8994
    Prev
    Next
    INDEX
    Explanations

    text describing the history and geographical makeup of the Diocese of Bisaccia

    oai_token-act-pair · gemini-2.0-flash

    non-English words or technical jargon

    np_token-act-pair-logits · gpt-4o-mini
    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
    principalTable
    -0.59
    存于互联网档案馆
    -0.58
    getLogger
    -0.57
     Yoh
    -0.51
    Datuak
    -0.50
     indoss
    -0.49
    ymce
    -0.48
    queur
    -0.47
    <?
    -0.47
    pushFollow
    -0.47
    POSITIVE LOGITS
    fjspx
    0.57
    SharedDtor
    0.54
    quiler
    0.51
    hmig
    0.47
    вку
    0.47
     oprot
    0.46
    enderror
    0.46
    исленность
    0.46
    tagext
    0.45
     prescri
    0.45
    Activations Density 0.393%

    No Known Activations