© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8133
    Prev
    Next
    INDEX
    Explanations

    words common in sports reporting

    oai_token-act-pair · gemini-2.0-flash

    Sports games

    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
     games
    -0.59
     Games
    -0.58
     게임
    -0.57
     Dostupné
    -0.55
     ""],
    -0.55
     kasarigan
    -0.54
    "])
    -0.54
     GAMES
    -0.53
    Games
    -0.52
    hoeddwyd
    -0.52
    POSITIVE LOGITS
    AddTagHelper
    0.82
    +#+
    0.70
    AndEndTag
    0.65
    OGND
    0.56
     CreateTagHelper
    0.54
    GOTREF
    0.52
    SIGNAL
    0.48
    transQ
    0.48
    ValueGeneration
    0.47
    olkata
    0.47
    Activations Density 6.116%

    No Known Activations