© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10331
    Prev
    Next
    INDEX
    Explanations

    words related to studies or checking something

    oai_token-act-pair · gemini-2.0-flash

    checking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    __":
    -0.89
    帖最后由
    -0.72
    __':
    -0.67
    __':
    -0.65
     mergeFrom
    -0.63
    __":
    -0.62
    XmlAccessType
    -0.59
     @"/
    -0.57
     vägen
    -0.56
     Wikimedijinoj
    -0.56
    POSITIVE LOGITS
     if
    2.86
    if
    2.25
     если
    1.84
     jika
    1.81
     dacă
    1.79
     If
    1.79
    If
    1.73
     якщо
    1.65
     nếu
    1.63
     jeśli
    1.57
    Activations Density 2.413%

    No Known Activations