© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5024
    Prev
    Next
    INDEX
    Explanations

    the letter "m" in various contractions and instances of first-person pronouns, along with other seemingly random words in the text.

    oai_token-act-pair · gemini-2.0-flash

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ########.
    -0.93
    rungsseite
    -0.93
     Administrativna
    -0.90
     kasarigan
    -0.84
    RegressionTest
    -0.83
     Roskov
    -0.81
    TintMode
    -0.79
     ModelExpression
    -0.77
    +#+#
    -0.77
     snippetHide
    -0.77
    POSITIVE LOGITS
     omnia
    0.46
     recycle
    0.45
     planches
    0.44
    recurring
    0.44
    esser
    0.43
     useDispatch
    0.41
     sibi
    0.41
    MILLISECONDS
    0.41
    .~(\
    0.40
    [::-
    0.40
    Activations Density 13.090%

    No Known Activations