© 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. 10248
    Prev
    Next
    INDEX
    Explanations

    fragments of conversations in French about software installation

    oai_token-act-pair · gemini-2.0-flash

    French forum

    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
    Negative Logits
    omock
    -0.49
     stages
    -0.48
    tetlen
    -0.46
    typeof
    -0.43
    lijken
    -0.43
     rega
    -0.42
    цыя
    -0.42
    TagMode
    -0.41
    WebServlet
    -0.41
    yntaxException
    -0.41
    POSITIVE LOGITS
    存于互联网档案馆
    0.63
     sur
    0.57
     sui
    0.56
     Administrativna
    0.56
    Sur
    0.54
     SUR
    0.54
    ={`/
    0.53
    FailureListener
    0.52
     NSCoder
    0.52
    }))
    0.52
    Activations Density 1.538%

    No Known Activations