© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9991
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to paleontology

    oai_token-act-pair · gemini-2.0-flash

    fossils and ancient species

    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
    providedIn
    -0.86
    bootstrapcdn
    -0.63
     commerciales
    -0.58
     veckor
    -0.56
     endwhile
    -0.55
     religieuses
    -0.54
     elettrica
    -0.53
     sayap
    -0.52
     كومونز
    -0.51
    stdafx
    -0.48
    POSITIVE LOGITS
     AssemblyCulture
    0.82
    @[+][
    0.80
    المكان
    0.61
     nahilalakip
    0.60
     noDo
    0.60
     Pand
    0.56
     Савезне
    0.55
     nod
    0.55
     EconPapers
    0.54
    anglès
    0.53
    Activations Density 1.069%

    No Known Activations