© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13456
    Prev
    Next
    INDEX
    Explanations

    a mix of words of endearment, words indicating something is new or unusual, proper titles such as "Majesty", and expressions of obligation or permission.

    oai_token-act-pair · gemini-2.0-flash

    story dialogues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     kaarangay
    -0.57
    ########.
    -0.55
     extérieures
    -0.50
     potr
    -0.50
    expandindo
    -0.48
     nahilalakip
    -0.48
    |+\
    -0.47
    civ
    -0.47
    ulx
    -0.47
     Dand
    -0.45
    POSITIVE LOGITS
    هما
    0.62
    naio
    0.62
     itſelf
    0.61
     quæ
    0.61
     AssemblyCulture
    0.58
     FetchType
    0.58
    PointerException
    0.57
    Qualifier
    0.56
     stör
    0.56
    AutoSize
    0.55
    Activations Density 1.597%

    No Known Activations