© 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. 5488
    Prev
    Next
    INDEX
    Explanations

    several concepts at once, including quantities, monetary values, weights, and items being carried.

    oai_token-act-pair · gemini-2.0-flash

    weight measurement units

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

    weight measurements

    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
     صوتيه
    -0.71
    évaluateur
    -0.63
    oara
    -0.59
    parsedMessage
    -0.57
    +#+#
    -0.54
    WebElementEntity
    -0.52
    UnsafeEnabled
    -0.51
     SEDS
    -0.50
    adaptiveStyles
    -0.50
    ⊰
    -0.49
    POSITIVE LOGITS
     pounds
    0.79
     kg
    0.73
     pound
    0.72
     lbs
    0.71
     کیلو
    0.70
    kg
    0.68
    lbs
    0.67
     lb
    0.67
     kilos
    0.66
    pounds
    0.65
    Activations Density 1.236%

    No Known Activations