© 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. 12604
    Prev
    Next
    INDEX
    Explanations

    band names

    oai_token-act-pair · gemini-2.0-flash

    Christy

    np_max-act · 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
     Zuge
    -0.53
     Last
    -0.53
    olese
    -0.52
     
    -0.52
      
    -0.51
    MENAFN
    -0.50
    blogs
    -0.49
     LGBTQ
    -0.46
     COVID
    -0.45
     https
    -0.45
    POSITIVE LOGITS
     nakalista
    1.05
    Хьажоргаш
    0.84
     Италијани
    0.82
     Efq
    0.81
     يتيمه
    0.81
    رشف
    0.80
     utafitiHapana
    0.77
    SharedDtor
    0.77
     Majefty
    0.76
    AsUp
    0.75
    Activations Density 3.134%

    No Known Activations