© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 4983
    Prev
    Next
    INDEX
    Explanations

    parenthesized expressions, URLs and code, and also lists of codes in medical papers

    oai_token-act-pair · gemini-2.0-flash

    Special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    tanleria
    -0.71
    !
    
    -0.65
    — 
    -0.63
    ...");
    
    -0.63
    NewLabel
    -0.63
     سكانية
    -0.60
     inconnu
    -0.59
    ?
    
    -0.59
    }%
    
    -0.58
    .}~\
    -0.58
    POSITIVE LOGITS
    <bos>
    2.19
    '
    0.62
    -
    0.56
    ’
    0.52
      
    0.49
    For
    0.48
    (
    0.47
     '\\;'
    0.47
     and
    0.47
    The
    0.47
    Activations Density 2.895%

    No Known Activations