© 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. 11928
    Prev
    Next
    INDEX
    Explanations

    words and phrases from Danish (or related Scandinavian languages) and the symbols /, & and –.

    oai_token-act-pair · gemini-2.0-flash

    Code/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
    contentLoaded
    -0.70
    quelize
    -0.64
    IntoConstraints
    -0.56
    oredCriteria
    -0.54
    RenderAtEndOf
    -0.53
     conch
    -0.53
    peutic
    -0.52
     Crusoe
    -0.51
     Piers
    -0.50
     Schofield
    -0.49
    POSITIVE LOGITS
     Theſe
    0.64
    aarrggbb
    0.63
     initComponents
    0.57
    WillAppear
    0.56
     الرياضيه
    0.52
     Efq
    0.52
    Autoritní
    0.50
    fromnode
    0.50
     Eſ
    0.50
    ută
    0.49
    Activations Density 0.147%

    No Known Activations