© 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. 14983
    Prev
    Next
    INDEX
    Explanations

    sentence punctuation and sentence structure words like "it is".

    oai_token-act-pair · gemini-2.0-flash

    past events or actions

    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
    kuuta
    -0.59
     Signalez
    -0.53
     raisin
    -0.50
    ingtones
    -0.50
    #
    -0.50
     NSCoder
    -0.50
     Sermons
    -0.49
     Trit
    -0.49
     MDC
    -0.47
     swig
    -0.47
    POSITIVE LOGITS
    accessed
    0.62
     located
    0.59
    located
    0.58
     filled
    0.56
     cortesía
    0.54
    Powered
    0.54
    脚注の使い方
    0.53
     composed
    0.52
     explored
    0.52
    Accessed
    0.52
    Activations Density 1.886%

    No Known Activations