© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12003
    Prev
    Next
    INDEX
    Explanations

    the preposition "in" followed by a number or something being processed

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    AndEndTag
    -0.59
     devriez
    -0.51
    かける
    -0.50
     للمعارف
    -0.50
    gius
    -0.47
     exécu
    -0.47
     '{@
    -0.46
    InitVars
    -0.46
    出版年
    -0.46
    のだ
    -0.46
    POSITIVE LOGITS
     Efq
    0.59
    multicolumn
    0.57
    BagLayout
    0.56
     cdti
    0.53
     manne
    0.52
    figsize
    0.52
     chandeliers
    0.52
     cohorts
    0.51
    PMailer
    0.51
    存于互联网档案馆
    0.51
    Activations Density 1.564%

    No Known Activations