© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    words related to Facebook accounts, phone numbers, and email addresses in Croatian

    oai_token-act-pair · gemini-2.0-flash

    Facebook account creation

    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
    Datuak
    -0.74
    ?
    -0.62
    Geplaatst
    -0.59
    ValueStyle
    -0.56
    ?}
    -0.56
    ()?
    -0.55
     تانيه
    -0.55
    ?".
    -0.54
     שוליים
    -0.54
    ?“
    -0.52
    POSITIVE LOGITS
    ,
    0.93
     and
    0.86
    .
    0.84
    性和
    0.65
     и
    0.65
     a
    0.63
    :
    0.60
     (
    0.57
     và
    0.57
    子和
    0.57
    Activations Density 2.953%

    No Known Activations