© 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. 15768
    Prev
    Next
    INDEX
    Explanations

    movie titles mixed with some common words in film reviews.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    kmäler
    -0.44
    Vanjske
    -0.38
    WriteString
    -0.37
     znac
    -0.37
    anyika
    -0.37
     possesso
    -0.35
     상세
    -0.35
    HandleFunc
    -0.34
    Get
    -0.34
     BNF
    -0.34
    POSITIVE LOGITS
    Datuak
    0.92
     ddelweddau
    0.82
    Personendaten
    0.79
    featureID
    0.77
     estekak
    0.75
    تقاوى
    0.70
    InvalidProtocol
    0.69
     ProtoMessage
    0.66
     linkovi
    0.66
     الرياضيه
    0.66
    Activations Density 0.167%

    No Known Activations