© 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. 11188
    Prev
    Next
    INDEX
    Explanations

    text about the Bifrost bridge and the realms of Asgard in Marvel Comics

    oai_token-act-pair · gemini-2.0-flash

    Nordic history/location mentions

    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
     Minnesota
    -1.60
    Minnesota
    -1.54
     MINNESOTA
    -1.34
     Norwegian
    -1.33
     Alaska
    -1.32
     Minn
    -1.31
     Minneapolis
    -1.30
     Alaskan
    -1.22
    Alaska
    -1.21
     MN
    -1.20
    POSITIVE LOGITS
    ponses
    0.57
     HttpResponse
    0.52
     Replay
    0.49
    campo
    0.48
    ough
    0.47
     Nilai
    0.45
     Ghat
    0.45
     fus
    0.45
    ayam
    0.45
     kiv
    0.44
    Activations Density 1.167%

    No Known Activations