© 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. 12986
    Prev
    Next
    INDEX
    Explanations

    computer code and configuration file snippets

    oai_token-act-pair · gemini-2.0-flash

    html

    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
    таратура
    -0.51
     saites
    -0.41
     himo
    -0.40
     utafitiHapana
    -0.38
     صوتيه
    -0.37
    KommentareTeilen
    -0.37
    ̍t
    -0.35
     ve
    -0.35
     mer
    -0.35
    queryInterface
    -0.34
    POSITIVE LOGITS
     myſelf
    1.05
     itſelf
    0.96
     Monfieur
    0.96
     Efq
    0.91
     himſelf
    0.87
     بيها
    0.86
     purpoſe
    0.84
     fubject
    0.82
     neceff
    0.81
     preſent
    0.79
    Activations Density 63.517%

    No Known Activations