© 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. 4098
    Prev
    Next
    INDEX
    Explanations

    verbs modified by "will," "would," "have" or "to".

    oai_token-act-pair · 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
     
    -0.57
     Don
    -0.56
    完
    -0.54
     $
    -0.54
     ‘
    -0.53
    ↵↵
    -0.52
     …
    -0.51
     No
    -0.51
     il
    -0.50
     I
    -0.50
    POSITIVE LOGITS
     myſelf
    1.20
     فريبيس
    1.19
     مشين
    1.06
     يتيمه
    1.06
     disambiguazione
    1.05
     pleaſure
    1.05
     Efq
    1.05
     Monfieur
    1.04
    .*")]
    1.04
    Rhestr
    1.03
    Activations Density 1.358%

    No Known Activations