© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8974
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles of creative works, with a bias towards personal names

    oai_token-act-pair · gemini-2.0-flash
    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
     betweenstory
    -0.63
     createState
    -0.62
     AssemblyCompany
    -0.60
     <>",
    -0.60
     BoxDecoration
    -0.50
    <bos>
    -0.50
     noires
    -0.50
     "'",
    -0.49
    posedge
    -0.48
    matchCondition
    -0.48
    POSITIVE LOGITS
     jeweils
    0.58
    respectively
    0.58
     both
    0.58
    Both
    0.57
    both
    0.57
     respectively
    0.56
     respectivamente
    0.53
     neg
    0.52
     Both
    0.50
    bootstrapcdn
    0.50
    Activations Density 1.083%

    No Known Activations