© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8285
    Prev
    Next
    INDEX
    Explanations

    dialogue or quotations

    oai_token-act-pair · gemini-2.0-flash

    ."

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ³.
    -0.54
    ReusableCell
    -0.54
    legende
    -0.52
     '.
    -0.52
    '.
    -0.50
    Portail
    -0.49
    __.
    -0.48
     appart
    -0.47
    mybatisplus
    -0.47
     OSP
    -0.47
    POSITIVE LOGITS
    ”
    0.73
    +:+
    0.72
    </
    0.70
    ScopeManager
    0.66
     cerimonia
    0.63
    “
    0.60
    ↵↵
    0.58
    
    0.57
    cnica
    0.55
    0.54
    Activations Density 2.974%
    No Known Activations