© 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. 2917
    Prev
    Next
    INDEX
    Explanations

    the word "interview" and related words or phrases

    oai_token-act-pair · gemini-2.0-flash

    interview

    np_max-act · gemini-2.0-flash

    interview

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    Negative Logits
     in
    -1.10
     an
    -1.01
    ,
    -0.98
     the
    -0.91
     for
    -0.89
     as
    -0.89
     he
    -0.88
     at
    -0.88
     her
    -0.88
     a
    -0.87
    POSITIVE LOGITS
     Theſe
    2.05
     Monfieur
    2.00
     itſelf
    1.85
     Jefus
    1.80
     Efq
    1.80
     myſelf
    1.79
     Houſe
    1.78
     Shakspeare
    1.73
     becauſe
    1.68
     Chriftian
    1.65
    Activations Density 2.730%

    No Known Activations