© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6738
    Prev
    Next
    INDEX
    Explanations

    the first person singular pronoun

    oai_token-act-pair · gemini-2.0-flash

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     
    -0.28
     ра
    -0.28
     at
    -0.25
    homonymie
    -0.24
     am
    -0.24
     за
    -0.23
     ri
    -0.23
    oa̍t
    -0.23
    fromCharCode
    -0.21
    хьтан
    -0.21
    POSITIVE LOGITS
     ſeveral
    0.88
     Monfieur
    0.86
     myſelf
    0.86
     itſelf
    0.82
     pleaſure
    0.79
     ſtate
    0.79
     Efq
    0.79
     poffe
    0.79
     himſelf
    0.79
     themſelves
    0.78
    Activations Density 3.872%

    No Known Activations