© 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. 3781
    Prev
    Next
    INDEX
    Explanations

    words that describe a concept or idea with an adjective

    oai_token-act-pair · gemini-2.0-flash

    basic

    np_max-act · gemini-2.0-flash

    types

    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
     Detailed
    -1.08
     Lightweight
    -1.05
     Traditional
    -1.05
     Regular
    -1.03
     Automatic
    -1.02
     Custom
    -1.02
     Automated
    -1.01
     Conditional
    -1.00
     Portable
    -1.00
     Private
    -0.99
    POSITIVE LOGITS
     simple
    0.80
     non
    0.79
     small
    0.71
     normal
    0.71
     strong
    0.69
     common
    0.66
     particular
    0.64
     different
    0.64
     full
    0.63
     single
    0.63
    Activations Density 4.995%

    No Known Activations