© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13833
    Prev
    Next
    INDEX
    Explanations

    mostly Danish words along with some Swedish words and some other words that begin a phrase

    oai_token-act-pair · gemini-2.0-flash

    Scandinavian languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    UnusedPrivate
    -0.81
     ErrIntOverflow
    -0.77
    ]--;
    -0.74
    extAlignment
    -0.72
    tonode
    -0.71
    tagHelperRunner
    -0.71
     CreateTagHelper
    -0.71
     ModelExpression
    -0.71
    multer
    -0.70
    ittäin
    -0.69
    POSITIVE LOGITS
    la
    0.45
    right
    0.42
    ṃ
    0.36
    XmlType
    0.35
     y
    0.35
    try
    0.34
     Right
    0.34
    Right
    0.33
     guar
    0.33
    netbeans
    0.33
    Activations Density 0.205%

    No Known Activations