© 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. 13349
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns followed immediately by a form of "to be".

    oai_token-act-pair · gemini-2.0-flash

    first-person pronouns and forms of 'to be'

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

    I'm

    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
     my
    -0.98
    my
    -0.95
     miei
    -0.91
     meu
    -0.91
     meus
    -0.88
    我的
    -0.83
     mijn
    -0.83
     minhas
    -0.82
     minha
    -0.80
     meines
    -0.78
    POSITIVE LOGITS
     his
    0.68
     not
    0.66
     here
    0.65
    EndInit
    0.61
     their
    0.61
     defaultstate
    0.57
     your
    0.57
     ready
    0.56
     CreateTagHelper
    0.53
     sua
    0.52
    Activations Density 1.362%

    No Known Activations