© 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. 15603
    Prev
    Next
    INDEX
    Explanations

    words describing negative economic conditions such as poverty and malnutrition

    oai_token-act-pair · gemini-2.0-flash

    severe conditions

    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
     Missing
    -1.23
    AndEndTag
    -1.22
    Missing
    -1.13
     missing
    -1.12
    missing
    -1.11
     omission
    -1.11
     absence
    -1.05
    absence
    -1.04
     Absence
    -1.03
     fehlen
    -1.02
    POSITIVE LOGITS
     chronic
    0.55
     severe
    0.52
     dire
    0.47
     acute
    0.46
     chronically
    0.45
     лет
    0.45
     severely
    0.44
    嚴重
    0.43
     sever
    0.41
     dangerously
    0.41
    Activations Density 3.595%

    No Known Activations