© 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. 2621
    Prev
    Next
    INDEX
    Explanations

    various terms related to marketing, sales, and offers, sometimes appearing in all caps

    oai_token-act-pair · gemini-2.0-flash

    more

    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
     We
    -0.60
     Working
    -0.58
    ArrowToggle
    -0.56
     Ours
    -0.54
     Order
    -0.54
    ölkerung
    -0.53
     Rough
    -0.52
     Here
    -0.52
     Operating
    -0.52
     Beneath
    -0.51
    POSITIVE LOGITS
     More
    1.48
    More
    1.24
    MORE
    0.93
     Additional
    0.89
     MORE
    0.84
     Other
    0.80
     Many
    0.77
    Additional
    0.72
     Such
    0.70
     Mehr
    0.68
    Activations Density 5.802%

    No Known Activations