© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4696
    Prev
    Next
    INDEX
    Explanations

    the word "Min" or "min"

    oai_token-act-pair · gemini-2.0-flash

    technical terminology related to programming or algorithms

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

    min

    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
     armes
    -0.49
    armes
    -0.45
     Estad
    -0.45
     due
    -0.45
    leg
    -0.45
     whatsoever
    -0.44
     trao
    -0.43
    ContextHolder
    -0.43
     byg
    -0.43
    чеб
    -0.43
    POSITIVE LOGITS
     متعلقه
    0.85
    aarrggbb
    0.84
     kasarigan
    0.81
    RenderAtEndOf
    0.73
    FunctionFlags
    0.72
    Дереккөздер
    0.69
     createSlice
    0.64
    fromnode
    0.63
    jScrollPane
    0.62
    مصادر
    0.61
    Activations Density 0.674%

    No Known Activations