© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3325
    Prev
    Next
    INDEX
    Explanations

    words and phrases about a person's association with organizations and activities

    oai_token-act-pair · gemini-2.0-flash

    ints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ngan
    -0.44
    </b>
    -0.42
    '">
    -0.39
     Col
    -0.38
    ñ
    -0.37
    </s>
    -0.36
     लिए
    -0.36
    vinger
    -0.36
    rhosis
    -0.35
    </strong>
    -0.35
    POSITIVE LOGITS
     Efq
    1.07
     Monfieur
    0.88
    IUrlHelper
    0.83
     poffe
    0.83
    IsContent
    0.81
     Majefty
    0.79
     leaſt
    0.78
     Hift
    0.77
     ་་
    0.76
     myſelf
    0.76
    Activations Density 2.585%

    No Known Activations