© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8111
    Prev
    Next
    INDEX
    Explanations

    the word "on" and words or short phrases that commonly follow it like "to," "and," or "what."

    oai_token-act-pair · gemini-2.0-flash

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     henvisninger
    -0.72
    <?
    -0.70
    ngdoc
    -0.66
    antMatchers
    -0.66
    DockStyle
    -0.65
     fédé
    -0.65
    adpleegd
    -0.65
    期刊论文
    -0.63
    Personensuche
    -0.62
     asiatique
    -0.62
    POSITIVE LOGITS
    isto
    0.46
    exitRule
    0.45
    fromnode
    0.44
     Kraw
    0.44
    hésite
    0.43
    NavController
    0.42
    !*\
    0.42
    GraphicsUnit
    0.42
     verd
    0.42
     Cle
    0.42
    Activations Density 3.655%

    No Known Activations