© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14064
    Prev
    Next
    INDEX
    Explanations

    words that provide context to a main idea.

    oai_token-act-pair · gemini-2.0-flash

    relevant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     related
    -1.23
     relevant
    -1.02
    Related
    -0.94
     Related
    -0.93
    Relevant
    -0.93
    related
    -0.90
    relevant
    -0.90
     Relevant
    -0.84
    相关
    -0.83
     associated
    -0.79
    POSITIVE LOGITS
    RenderAtEndOf
    0.86
     esternos
    0.84
     Efq
    0.82
     "$@"
    0.74
     cauſe
    0.69
     nonUne
    0.68
     myſelf
    0.68
     تانيه
    0.67
    
    0.66
     ſtre
    0.65
    Activations Density 28.527%

    No Known Activations