© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5519
    Prev
    Next
    INDEX
    Explanations

    the number 5 when used in a numerical code

    oai_token-act-pair · gemini-2.0-flash

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ImageContext
    -0.66
     cenar
    -0.63
     quæ
    -0.63
    kháu
    -0.61
     vecchi
    -0.61
     allmän
    -0.60
     frasi
    -0.60
     sélectionnés
    -0.60
    Datuak
    -0.60
     EconPapers
    -0.59
    POSITIVE LOGITS
    saraba
    0.53
    ($('#
    0.52
    :+:
    0.51
    xFFFF
    0.51
     $[
    0.50
    chées
    0.50
    ITABLE
    0.50
    dé
    0.50
     [
    0.50
    VersionUID
    0.49
    Activations Density 0.441%

    No Known Activations