© 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. 7634
    Prev
    Next
    INDEX
    Explanations

    menu and restaurant review snippets

    oai_token-act-pair · gemini-2.0-flash

    special characters and foreign words

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

    period

    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
    __':
    -0.63
    
    -0.59
     '\\;'
    -0.59
    CppMethod
    -0.57
    __':
    -0.55
     Coen
    -0.55
    KommentareTeilen
    -0.54
    RTGC
    -0.54
    󠁴
    -0.54
     Процитовано
    -0.53
    POSITIVE LOGITS
    ApiException
    0.49
    ènement
    0.48
    insegna
    0.47
    GHIJKLM
    0.46
    下载附件
    0.45
    hänge
    0.45
    はじめに
    0.45
    Extinguishing
    0.45
     if
    0.44
     try
    0.43
    Activations Density 0.970%

    No Known Activations