© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16280
    Prev
    Next
    INDEX
    Explanations

    words related to game playing and stone working

    oai_token-act-pair · gemini-2.0-flash

    Expansion and expanding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     expansion
    -2.97
     Expansion
    -2.91
     expand
    -2.69
     expansions
    -2.64
    Expansion
    -2.64
     expanded
    -2.61
    expansion
    -2.58
     expanding
    -2.56
     expands
    -2.52
     Expand
    -2.50
    POSITIVE LOGITS
    nalités
    0.53
    GEBURTSDATUM
    0.52
    FormTagHelper
    0.52
    AsUp
    0.50
    interopRequire
    0.48
    ptonshire
    0.47
    っこう
    0.46
    *~*~
    0.46
    hdysval
    0.45
    Rè
    0.45
    Activations Density 3.488%

    No Known Activations