© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8174
    Prev
    Next
    INDEX
    Explanations

    sentence boundaries and short phrases

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ExecuteAsync
    -1.01
    ✨:
    -0.91
    +:+
    -0.91
    \{\\
    -0.88
    UserScript
    -0.86
    InputBorder
    -0.86
     AssemblyCompany
    -0.83
     صوتيه
    -0.82
     مشين
    -0.79
    matchCondition
    -0.78
    POSITIVE LOGITS
     
    0.65
     i
    0.50
     études
    0.49
     I
    0.48
     कुछ
    0.47
     o
    0.46
    ↵↵
    0.46
    ↵↵↵
    0.45
     înal
    0.44
     (
    0.43
    Activations Density 1.020%

    No Known Activations