© 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. 2014
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs, especially regarding dialogue

    oai_token-act-pair · gemini-2.0-flash

    well, yes, i

    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
    <bos>
    -0.72
    “
    -0.62
    ว่า
    -0.52
    :
    -0.52
     “
    -0.52
     saying
    -0.50
    ”
    -0.50
     zákaz
    -0.49
     ‘
    -0.48
    INFORM
    -0.48
    POSITIVE LOGITS
    出版年
    0.73
     <=",
    0.70
    Diwedd
    0.70
    tagHelperRunner
    0.70
     cherchés
    0.67
    AutoScaleMode
    0.66
    LayoutStyle
    0.66
    Reprodução
    0.62
    الدراسه
    0.60
    DeleteBehavior
    0.60
    Activations Density 3.973%

    No Known Activations