© 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. 11962
    Prev
    Next
    INDEX
    Explanations

    the word "active" and words relating to it

    oai_token-act-pair · gemini-2.0-flash

    active

    np_max-act · gemini-2.0-flash

    active

    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
    м
    -0.84
    er
    -0.81
    ig
    -0.77
    rog
    -0.72
    es
    -0.70
    ­
    -0.70
    ed
    -0.68
    em
    -0.68
    е
    -0.68
    ize
    -0.68
    POSITIVE LOGITS
     sauvages
    1.05
     blessés
    1.04
     prêts
    1.04
     détruit
    1.03
     faciles
    1.03
     normaux
    1.02
     oublier
    1.01
     plufieurs
    1.00
     définiti
    1.00
     dedans
    1.00
    Activations Density 1.467%

    No Known Activations