© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14981
    Prev
    Next
    INDEX
    Explanations

    words relating to marine biology, specifically those related to shrimp and vibrio

    oai_token-act-pair · gemini-2.0-flash

    aquatic environments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    StoryboardSegue
    -0.71
    TagMode
    -0.66
     متعلقه
    -0.49
     Ceará
    -0.48
     Upan
    -0.45
     Bead
    -0.43
     Cister
    -0.43
    wortet
    -0.42
     Huguen
    -0.42
     roe
    -0.41
    POSITIVE LOGITS
     pulumi
    0.76
    oredCriteria
    0.61
    SharedDtor
    0.61
    mallows
    0.58
    IMPORTED
    0.56
    AccessorTable
    0.56
    daille
    0.54
     Den
    0.54
    EDEFAULT
    0.53
    NameInMap
    0.52
    Activations Density 1.237%

    No Known Activations