© 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. 9717
    Prev
    Next
    INDEX
    Explanations

    the letter 'G' appearing as an initial

    oai_token-act-pair · gemini-2.0-flash

    G

    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
    PasswordEncoder
    -0.61
    qrstuvwxyz
    -0.58
    <bos>
    -0.55
    astify
    -0.52
    bable
    -0.50
     statt
    -0.50
    SerializedName
    -0.49
    sdk
    -0.49
    BrowserModule
    -0.48
    apimachinery
    -0.48
    POSITIVE LOGITS
    StructEnd
    0.73
    Personensuche
    0.69
     typelib
    0.64
    RTGC
    0.62
     avoient
    0.60
     étoient
    0.58
     चीज़ों
    0.56
     intptr
    0.55
    Сон
    0.54
     himo
    0.53
    Activations Density 0.302%

    No Known Activations