© 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. 14469
    Prev
    Next
    INDEX
    Explanations

    prepositions

    oai_token-act-pair · gemini-2.0-flash

    various uses of the word 'as'

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

    as

    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
     autorytatywna
    -0.64
    TagMode
    -0.64
     linkovi
    -0.63
     nahilalakip
    -0.60
     onOptions
    -0.59
     endwhile
    -0.58
    Autoritní
    -0.57
    iprot
    -0.57
    Personendaten
    -0.57
     كومونز
    -0.56
    POSITIVE LOGITS
     a
    0.91
     an
    0.72
     boundary
    0.56
    '][]
    0.52
    ]='\
    0.52
     ke
    0.51
    stepping
    0.51
     Mode
    0.51
    pires
    0.50
    abit
    0.49
    Activations Density 13.513%

    No Known Activations