© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4016
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and related family terms

    oai_token-act-pair · gemini-2.0-flash

    first-person singular pronouns and related phrases

    np_token-act-pair-logits · gpt-4o-mini

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AndEndTag
    -0.87
     itſelf
    -0.85
     neceffary
    -0.73
     uſe
    -0.71
     springfox
    -0.69
    存于互联网档案馆
    -0.69
     leaft
    -0.68
     faſt
    -0.66
    DockStyle
    -0.66
     resourceCulture
    -0.66
    POSITIVE LOGITS
     met
    0.50
     always
    0.48
     sering
    0.46
    tvguidetime
    0.44
     Loved
    0.43
     rate
    0.40
    chappen
    0.40
     meny
    0.40
     best
    0.39
    den
    0.39
    Activations Density 0.639%

    No Known Activations