© 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. 11279
    Prev
    Next
    INDEX
    Explanations

    words related to Facebook and foreign languages

    oai_token-act-pair · gemini-2.0-flash

    non-English

    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
    tagext
    -0.63
    NameInMap
    -0.60
    PreferredItem
    -0.56
    enterOuterAlt
    -0.55
     continúas
    -0.54
    abestanden
    -0.52
     صوتيه
    -0.48
    jectures
    -0.47
    join
    -0.46
    сылкі
    -0.46
    POSITIVE LOGITS
    featureID
    0.66
    entista
    0.55
    viert
    0.53
    kegaard
    0.53
    Grit
    0.51
    
    0.51
    Dund
    0.50
     kaynağından
    0.50
    IsMutable
    0.49
    NewGuid
    0.48
    Activations Density 0.126%

    No Known Activations