© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14563
    Prev
    Next
    INDEX
    Explanations

    the word "Nor" or "Sou" or any words starting with those capitalized letter combinations

    oai_token-act-pair · gemini-2.0-flash

    Nor

    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
    PREFERRED
    -0.49
    maphore
    -0.47
    CodeAttribute
    -0.47
    jei
    -0.47
    masi
    -0.47
    ivar
    -0.47
     Reporter
    -0.46
    irical
    -0.46
     правда
    -0.46
    îtres
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.68
    новниш
    0.68
     utafitiHapana
    0.67
    DeleteBehavior
    0.66
    ArrowToggle
    0.61
    Personendaten
    0.61
     muualla
    0.60
    ScopeManager
    0.60
    AndEndTag
    0.60
    addCriterion
    0.57
    Activations Density 0.211%

    No Known Activations