© 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. 12390
    Prev
    Next
    INDEX
    Explanations

    words ending in "maker" that refer to people who create or decide things

    oai_token-act-pair · gemini-2.0-flash

    maker

    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
     ſche
    -0.75
     ―――――
    -0.75
     Houſe
    -0.72
     Monfieur
    -0.71
     Reſ
    -0.68
     ་་
    -0.66
     Eſ
    -0.66
     pleaſure
    -0.65
     Majefty
    -0.65
     Chriftian
    -0.63
    POSITIVE LOGITS
     esternos
    0.97
     ويكيميديا
    0.88
     snippetHide
    0.88
     ujednoznacz
    0.88
     disponibilités
    0.87
    ngdoc
    0.87
    ContentAsync
    0.87
    abestanden
    0.83
    帖最后由
    0.82
    endphp
    0.81
    Activations Density 1.009%

    No Known Activations