© 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. 3258
    Prev
    Next
    INDEX
    Explanations

    the word "lessons"

    oai_token-act-pair · gemini-2.0-flash

    lessons

    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
    RenderAtEndOf
    -0.98
     Efq
    -0.95
     Theſe
    -0.90
     <>",
    -0.89
     Hift
    -0.88
    ThroughAttribute
    -0.88
     avoient
    -0.86
     termica
    -0.86
     illustrazione
    -0.84
     fermés
    -0.84
    POSITIVE LOGITS
     real
    0.59
     non
    0.57
     no
    0.57
     a
    0.56
     tos
    0.55
     regular
    0.55
     most
    0.53
    ogno
    0.53
     sp
    0.52
     w
    0.51
    Activations Density 0.829%

    No Known Activations