© 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. 3013
    Prev
    Next
    INDEX
    Explanations

    the word "manual" and words associated with documentation or printed materials

    oai_token-act-pair · gemini-2.0-flash

    manual

    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
     morire
    -0.92
     réguli
    -0.89
     piú
    -0.88
     fermés
    -0.86
     nemici
    -0.83
     giapp
    -0.83
     élevées
    -0.83
     ferons
    -0.82
     éduc
    -0.82
     mourir
    -0.80
    POSITIVE LOGITS
    ]!=
    0.64
    outines
    0.64
    heets
    0.63
    ')):
    0.63
     cal
    0.62
    <0xF3>
    0.62
     pec
    0.62
    źdz
    0.62
    hObject
    0.61
    uests
    0.60
    Activations Density 2.481%

    No Known Activations