© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10972
    Prev
    Next
    INDEX
    Explanations

    numbers, units of measure, and references to observation within scientific writing

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     microns
    -0.80
    micro
    -0.77
     micron
    -0.77
     micro
    -0.76
     Micro
    -0.74
    Micro
    -0.73
    \{\\
    -0.72
     µ
    -0.71
     mic
    -0.71
    Personendaten
    -0.71
    POSITIVE LOGITS
     Man
    0.49
    Man
    0.45
     collè
    0.43
    tonode
    0.42
     duele
    0.42
     hard
    0.41
    jsonwebtoken
    0.41
    mett
    0.41
    GeoNames
    0.41
    addHandler
    0.41
    Activations Density 1.295%

    No Known Activations