© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5057
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, especially those starting with "M", "S", "V", "G", "L", "T", "F", "C", "P", or "IM"

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords and phrases

    np_token-act-pair-logits · gpt-4o-mini

    M

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     initComponents
    -0.55
     ovale
    -0.52
     liberi
    -0.49
     desaf
    -0.44
    PERFORMANCE
    -0.43
     cirrhosis
    -0.43
     recommandons
    -0.43
     stimmt
    -0.42
    adjoint
    -0.42
     cana
    -0.42
    POSITIVE LOGITS
    findpost
    0.65
    Autoritní
    0.64
    UpInside
    0.63
    DockStyle
    0.62
    FilterChain
    0.61
     <=",
    0.60
    InjectAttribute
    0.59
    asker
    0.58
     InputDecoration
    0.56
     تانيه
    0.56
    Activations Density 1.290%

    No Known Activations