© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3883
    Prev
    Next
    INDEX
    Explanations

    passages of text that discuss managers

    oai_token-act-pair · gemini-2.0-flash

    manager

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    SharedDtor
    -0.85
    NameInMap
    -0.80
    twimg
    -0.77
     '\\;'
    -0.77
     pitié
    -0.75
     dépens
    -0.74
    saraba
    -0.74
     ISNI
    -0.72
    šanai
    -0.71
    @[+][
    -0.71
    POSITIVE LOGITS
    ADO
    0.64
    zare
    0.61
    Gön
    0.60
    сло
    0.60
    [^
    0.59
    batore
    0.58
    conio
    0.56
    compan
    0.54
    ORE
    0.54
    0.54
    Activations Density 1.170%

    No Known Activations