© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2717
    Prev
    Next
    INDEX
    Explanations

    the first-person pronoun 'I' followed by the contraction "'ve"

    oai_token-act-pair · gemini-2.0-flash

    I/you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    OGND
    -0.96
    #+#
    -0.88
    wapV
    -0.74
     تضيفلها
    -0.72
     estekak
    -0.72
    AddHtmlAttribute
    -0.71
    LookAnd
    -0.71
    gonic
    -0.71
     Efq
    -0.70
    findpost
    -0.69
    POSITIVE LOGITS
     you
    0.47
    ad
    0.47
     potete
    0.45
     now
    0.43
    ningarna
    0.41
     it
    0.40
    CU
    0.39
    ajo
    0.39
    cu
    0.39
    Portail
    0.36
    Activations Density 0.569%

    No Known Activations