© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11068
    Prev
    Next
    INDEX
    Explanations

    various kinds of ID numbers

    oai_token-act-pair · gemini-2.0-flash

    code or numerical sequences

    np_max-act · gemini-2.0-flash

    say "hex digits"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    XmlAccessType
    -0.86
    sizeCache
    -0.84
    protoimpl
    -0.84
    parsedMessage
    -0.80
    setVerticalGroup
    -0.76
    LookAnd
    -0.74
    SBATCH
    -0.73
     betweenstory
    -0.73
     invokingState
    -0.72
    CloseOperation
    -0.71
    POSITIVE LOGITS
     lomb
    0.49
    HOW
    0.45
    Com
    0.43
     mental
    0.42
    com
    0.42
    問
    0.41
    Mvc
    0.40
     mutil
    0.40
    秀
    0.40
    A
    0.39
    Activations Density 1.578%

    No Known Activations