© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11803
    Prev
    Next
    INDEX
    Explanations

    mentions of difficulties or uncertainty someone is experiencing.

    oai_token-act-pair · gemini-2.0-flash

    driving

    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
    ValueStyle
    -0.54
    lijken
    -0.51
     bancada
    -0.48
    viewDid
    -0.48
     Parla
    -0.47
    stand
    -0.47
    rungsseite
    -0.46
    jLabel
    -0.46
     timedelta
    -0.45
    øn
    -0.45
    POSITIVE LOGITS
     drives
    1.16
     driving
    1.10
     drive
    1.07
     drove
    1.05
    driving
    1.01
     Drives
    1.01
    drives
    0.98
    drive
    0.96
    Driving
    0.95
     bug
    0.91
    Activations Density 2.458%

    No Known Activations