© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3886
    Prev
    Next
    INDEX
    Explanations

    the word "ended" and related verbs

    oai_token-act-pair · gemini-2.0-flash

    forms of "end" and variations of "up"

    np_token-act-pair-logits · gpt-4o-mini

    end

    np_max-act-logits · gemini-2.0-flash
    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
    principalColumn
    -0.70
    borderSide
    -0.64
    Personendaten
    -0.63
    writeFieldEnd
    -0.62
     pinulongan
    -0.61
     ErrIntOverflow
    -0.61
    Хьажоргаш
    -0.60
     Winaray
    -0.59
    Diweddarwch
    -0.58
    AnchorStyles
    -0.57
    POSITIVE LOGITS
     up
    1.65
     Up
    0.97
    up
    0.95
    Up
    0.93
     UP
    0.73
     upto
    0.63
    upto
    0.59
     lên
    0.57
    ups
    0.52
     вверх
    0.52
    Activations Density 0.587%

    No Known Activations