© 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. 14144
    Prev
    Next
    INDEX
    Explanations

    language from personal perspectives related to race

    oai_token-act-pair · gemini-2.0-flash

    white

    np_max-act · 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
    Equation
    -0.50
    makeConstraints
    -0.49
    JNIEnv
    -0.45
     оригіналу
    -0.45
    entrySet
    -0.44
     pyplot
    -0.43
     Процитовано
    -0.42
    摩
    -0.41
     rgba
    -0.41
    ügen
    -0.41
    POSITIVE LOGITS
    LookAnd
    0.94
     pleaſure
    0.68
     متعلقه
    0.63
    expandindo
    0.63
    rungsseite
    0.62
     purpoſe
    0.62
     actuels
    0.62
     définiti
    0.60
    PerformLayout
    0.60
    Rhestr
    0.60
    Activations Density 1.457%

    No Known Activations