© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4570
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with perfection or agreement

    oai_token-act-pair · gemini-2.0-flash

    perfectly

    np_max-act · gemini-2.0-flash

    perfectly

    np_max-act-logits · gpt-5-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.92
     the
    -0.86
     En
    -0.80
     Qu
    -0.77
     He
    -0.75
    the
    -0.73
     Bar
    -0.73
     Co
    -0.73
     Ho
    -0.73
    <eos>
    -0.71
    POSITIVE LOGITS
     myſelf
    1.38
     Majefty
    1.27
     ſche
    1.25
     itſelf
    1.24
     Monfieur
    1.23
     ſind
    1.20
     purpoſe
    1.18
     Anſ
    1.16
     Jefus
    1.15
     ་་
    1.15
    Activations Density 2.339%

    No Known Activations