© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8393
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating dates, locations, descriptions and relationships between things

    oai_token-act-pair · gemini-2.0-flash

    Scientific figures and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     plonge
    -0.44
     répé
    -0.42
     mano
    -0.41
    buh
    -0.41
    views
    -0.40
    fjspx
    -0.40
     متعلقه
    -0.40
    どころ
    -0.40
    Diver
    -0.40
    раздо
    -0.39
    POSITIVE LOGITS
    ContentAlignment
    0.63
     unknownFields
    0.63
    AutoField
    0.61
    UMBIA
    0.61
     مواليد
    0.60
     MainAxisSize
    0.60
    Diwedd
    0.59
    ValueGeneration
    0.59
    ThroughAttribute
    0.59
    BorderFactory
    0.57
    Activations Density 0.584%

    No Known Activations