© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1296
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and possessive pronouns ("I", "me", "my").

    oai_token-act-pair · gemini-2.0-flash

    my

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.64
    Autoritní
    -0.63
    WaitGroup
    -0.59
    Personensuche
    -0.59
    UnusedPrivate
    -0.57
     contextLoads
    -0.57
    Their
    -0.56
     herido
    -0.55
     незавершена
    -0.55
    berdayakan
    -0.55
    POSITIVE LOGITS
     wife
    0.69
     daughter
    0.61
    anmar
    0.60
     husband
    0.60
     son
    0.60
    riad
    0.57
     life
    0.55
     usual
    0.54
     own
    0.53
     previous
    0.52
    Activations Density 5.792%

    No Known Activations