© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14315
    Prev
    Next
    INDEX
    Explanations

    the honorific title "Mr." followed by a surname, suggesting it identifies individuals

    oai_token-act-pair · gemini-2.0-flash

    Mr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.93
     
    -0.89
    ↵
    -0.81
      
    -0.72
     and
    -0.65
     I
    -0.62
     The
    -0.62
     A
    -0.61
     "
    -0.61
    .
    -0.60
    POSITIVE LOGITS
     resourceCulture
    1.07
    Билгалдахарш
    1.07
     tartalomajánló
    1.05
     تانيه
    1.05
     Efq
    1.02
    Hochspringen
    1.02
     &___
    1.01
     ſtate
    0.97
     <<<<<<<<<<<<<<
    0.97
    InjectAttribute
    0.96
    Activations Density 2.707%

    No Known Activations