© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6344
    Prev
    Next
    INDEX
    Explanations

    phrases containing "come to mind" and references to one's own mind/thoughts

    oai_token-act-pair · gemini-2.0-flash

    Possessive pronouns

    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
    Not in Any Lists

    No Comments

    Negative Logits
     uſe
    -0.66
     onAnimation
    -0.65
     الرياضيه
    -0.65
    twimg
    -0.63
     lenker
    -0.59
    gäng
    -0.57
    ,:),
    -0.56
    saraba
    -0.56
     Jefus
    -0.56
     CURIAM
    -0.55
    POSITIVE LOGITS
     your
    0.72
    your
    0.56
     mi
    0.54
     my
    0.53
     minha
    0.52
    Mi
    0.49
     Mi
    0.47
    min
    0.45
     Min
    0.44
     votre
    0.44
    Activations Density 0.974%

    No Known Activations