© 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. 13442
    Prev
    Next
    INDEX
    Explanations

    Danish words, particularly those appearing in movie titles

    oai_token-act-pair · gemini-2.0-flash

    ene

    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
    GEBURTSDATUM
    -1.08
    tagHelperRunner
    -0.62
    KURZBESCHREIBUNG
    -0.61
     Normdatei
    -0.57
    AndEndTag
    -0.56
    AndroidJUnit
    -0.56
    исленность
    -0.52
    IsContent
    -0.50
     صوتيه
    -0.50
    ConstraintMaker
    -0.50
    POSITIVE LOGITS
    ergic
    0.54
    jores
    0.51
    BrowserModule
    0.49
    nościo
    0.49
    Искәрмәләр
    0.48
    ourable
    0.48
    amitié
    0.48
     importer
    0.47
     swit
    0.47
    dorp
    0.47
    Activations Density 0.432%

    No Known Activations