© 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. 8720
    Prev
    Next
    INDEX
    Explanations

    the word rate, speed, level, or temperature along with other words that could define their context in technical writing

    oai_token-act-pair · gemini-2.0-flash

    prepositions and their positional usage

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

    rate

    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
     Vikipedi
    -0.75
     дописавши
    -0.74
    ValueStyle
    -0.74
    apunov
    -0.66
    AsUp
    -0.65
     beginnetje
    -0.64
     ModelExpression
    -0.62
    تقاوى
    -0.62
    abetes
    -0.61
     незавершена
    -0.61
    POSITIVE LOGITS
     at
    2.53
    At
    1.34
     At
    1.33
    at
    1.27
     tại
    1.21
     	e
    0.89
     ở
    0.84
     AT
    0.77
     @
    0.66
     bei
    0.65
    Activations Density 2.022%

    No Known Activations