© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6183
    Prev
    Next
    INDEX
    Explanations

    pronouns, conjunctions, prepositions, and some common verbs, especially words that connect clauses or phrases

    oai_token-act-pair · gemini-2.0-flash

    Personal stories and experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
      (
    -0.50
     ProtoMessage
    -0.48
     N
    -0.45
    endwhile
    -0.44
     mxArray
    -0.44
    CHI
    -0.43
    hug
    -0.43
    APPRO
    -0.41
     vers
    -0.41
     S
    -0.41
    POSITIVE LOGITS
    MessageOf
    0.83
    SpringBootTest
    0.72
     Bourgoin
    0.69
    principalTable
    0.67
    antaranya
    0.66
     Majefty
    0.64
     Forumite
    0.64
     morire
    0.63
    Бахар
    0.63
     fubject
    0.63
    Activations Density 3.333%

    No Known Activations