© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10319
    Prev
    Next
    INDEX
    Explanations

    the beginning of the word "retaliation" or "retweeting".

    oai_token-act-pair · gemini-2.0-flash

    ret

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Her
    -0.38
     re
    -0.36
    ẫu
    -0.35
     X
    -0.34
     relativo
    -0.33
    zburg
    -0.32
    X
    -0.31
     retracted
    -0.31
     terug
    -0.31
    [::-
    -0.30
    POSITIVE LOGITS
    ########.
    0.94
     estekak
    0.86
    oa̍t
    0.78
     Normdatei
    0.78
    Vidite
    0.74
     Wikispecies
    0.73
    enumii
    0.72
    (!__
    0.72
    setVerticalGroup
    0.71
    CppMethod
    0.70
    Activations Density 1.245%

    No Known Activations