© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13325
    Prev
    Next
    INDEX
    Explanations

    the word 'year' or 'years', likely in reference to academic durations

    oai_token-act-pair · gemini-2.0-flash

    year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.89
    StoryboardSegue
    -0.76
    ChildScrollView
    -0.67
    arakhand
    -0.66
    ousands
    -0.64
    ArrowToggle
    -0.63
    ousand
    -0.61
    esterday
    -0.61
     weeks
    -0.60
    Manbalar
    -0.60
    POSITIVE LOGITS
    findpost
    0.56
    ArgsConstructor
    0.55
    entennial
    0.52
    ########.
    0.51
     समीक्षक
    0.50
    eso
    0.50
     croit
    0.50
    #+#
    0.50
    ilen
    0.49
    jant
    0.49
    Activations Density 0.379%

    No Known Activations