© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11924
    Prev
    Next
    INDEX
    Explanations

    words and phrases including "off", combined with domain-specific terms like "burn-in" or "cut" prefixing "off."

    oai_token-act-pair · gemini-2.0-flash

    technical cut-off values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     judiciales
    -0.60
    Diwedd
    -0.57
    nextLine
    -0.51
    mitglieder
    -0.50
     policiales
    -0.48
     sociali
    -0.46
    peicher
    -0.45
     «
    -0.45
     educativas
    -0.45
      
    -0.45
    POSITIVE LOGITS
     ―――――
    0.74
     itſelf
    0.71
    Personensuche
    0.71
     pleaſure
    0.70
    ValueStyle
    0.70
     beginnetje
    0.65
    TemporalType
    0.65
     myſelf
    0.63
    allure
    0.62
     ſche
    0.62
    Activations Density 0.842%

    No Known Activations