© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3866
    Prev
    Next
    INDEX
    Explanations

    seemingly random and inconsistent numbers in text

    oai_token-act-pair · gemini-2.0-flash

    legal jargon and references

    np_token-act-pair-logits · gpt-4o-mini
    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
    featureID
    -1.05
    parsedMessage
    -0.91
    IVEREF
    -0.85
    SharedDtor
    -0.85
     kaarangay
    -0.84
    LookAnd
    -0.84
     الرياضيه
    -0.81
    WebElementEntity
    -0.78
    tagext
    -0.76
    ScopeManager
    -0.75
    POSITIVE LOGITS
    urlopen
    0.48
    zuma
    0.44
    urn
    0.43
     ob
    0.42
     handleMessage
    0.41
     In
    0.41
    :(
    0.40
    lav
    0.40
    <eos>
    0.39
    mel
    0.39
    Activations Density 0.894%

    No Known Activations