© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2668
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets and genetic sequences

    oai_token-act-pair · gemini-2.0-flash

    DNA sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     JpaRepository
    -0.68
    HasForeignKey
    -0.63
    findpost
    -0.60
    phrine
    -0.58
    EndContext
    -0.56
    GEBURTSDATUM
    -0.55
     Mérimée
    -0.55
     ModelExpression
    -0.52
     Paro
    -0.51
    penup
    -0.50
    POSITIVE LOGITS
    enumii
    0.59
    τια
    0.52
     ostavi
    0.48
    romolecules
    0.47
    elfare
    0.47
     betweenstory
    0.47
    arest
    0.47
    veux
    0.46
     SUDOC
    0.46
    mergeFrom
    0.46
    Activations Density 1.593%

    No Known Activations