© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7041
    Prev
    Next
    INDEX
    Explanations

    words or short phrases in the French language

    oai_token-act-pair · gemini-2.0-flash

    other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     [*]
    -0.52
     lệ
    -0.39
    НИК
    -0.38
     public
    -0.35
    ignez
    -0.35
    mons
    -0.35
     Physiol
    -0.34
    ждествен
    -0.34
    ari
    -0.34
     Ch
    -0.33
    POSITIVE LOGITS
     Monfieur
    1.02
     Jefus
    1.00
     himſelf
    0.95
     Theſe
    0.94
     pleaſure
    0.92
     myſelf
    0.91
     itſelf
    0.90
     ſeveral
    0.90
     whoſe
    0.89
    AsUp
    0.88
    Activations Density 1.067%

    No Known Activations