© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10681
    Prev
    Next
    INDEX
    Explanations

    code and code-like text

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     ‘
    -0.47
     et
    -0.43
     ré
    -0.41
    étr
    -0.41
     min
    -0.41
    ertos
    -0.41
    heben
    -0.40
    umin
    -0.39
    nati
    -0.39
    anes
    -0.39
    POSITIVE LOGITS
     myſelf
    0.99
     themſelves
    0.93
     himſelf
    0.92
     poffible
    0.90
     Efq
    0.90
     Monfieur
    0.87
     purpoſe
    0.85
     itſelf
    0.85
     whoſe
    0.84
     pleaſure
    0.81
    Activations Density 0.233%

    No Known Activations