© 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. 4808
    Prev
    Next
    INDEX
    Explanations

    the pronouns "we", "our", "us", and "ourselves"

    oai_token-act-pair · gemini-2.0-flash

    We

    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
    +#+#
    -0.71
    IUrlHelper
    -0.66
    Personendaten
    -0.64
    الحياه
    -0.64
    gridy
    -0.60
    ьаж
    -0.60
     CommonModule
    -0.60
    IsMutable
    -0.60
    <bos>
    -0.58
    addContainerGap
    -0.57
    POSITIVE LOGITS
    enschappen
    0.51
    citizen
    0.50
    Citizen
    0.49
    гули
    0.49
     realize
    0.49
     realise
    0.48
     tweet
    0.46
    ibrator
    0.46
    MfG
    0.46
     Citizen
    0.45
    Activations Density 2.308%

    No Known Activations