© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 631
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     it
    -1.00
    IsContent
    -0.73
    GenerationType
    -0.69
    It
    -0.68
    Rhestr
    -0.66
    __',
    -0.65
     betweenstory
    -0.64
     itr
    -0.62
     It
    -0.61
    it
    -0.59
    POSITIVE LOGITS
    pexpr
    0.49
     OnInit
    0.46
    IZONA
    0.43
    ModelSerializer
    0.43
    πάρχ
    0.42
     klubben
    0.40
     ۲۰۱
    0.40
    ArgsConstructor
    0.40
     الأع
    0.40
    isdigit
    0.38
    Activations Density 1.269%

    No Known Activations