© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7982
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words, depending on the context

    oai_token-act-pair · gemini-2.0-flash

    terms related to processes or actions of evaluation

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     protecting
    -0.66
     evaluating
    -0.62
     reacting
    -0.61
     educating
    -0.60
     inspecting
    -0.60
     executing
    -0.60
     promoting
    -0.59
     managing
    -0.59
     transferring
    -0.59
     transporting
    -0.59
    POSITIVE LOGITS
     derivation
    0.92
     creation
    0.88
     preservation
    0.84
    creation
    0.83
     detection
    0.82
     realization
    0.82
     acquisition
    0.81
     identification
    0.80
     completion
    0.79
     avoidance
    0.79
    Activations Density 5.065%

    No Known Activations