© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 685
    Prev
    Next
    INDEX
    Explanations

    mathematical and/or scientific notation including units of measure

    oai_token-act-pair · gemini-2.0-flash

    inverse

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     disturb
    -0.93
     disturbed
    -0.91
     DIST
    -0.86
     distur
    -0.82
     pertur
    -0.82
    kháu
    -0.82
     disrupt
    -0.82
     disturbance
    -0.81
     Disturb
    -0.81
     Dis
    -0.81
    POSITIVE LOGITS
    ^{-
    1.05
    }^{-
    0.98
     inverse
    0.88
     }^{-
    0.80
    )^{-
    0.79
    ]^{-
    0.78
     ^{-
    0.77
    ^(-
    0.75
    inverse
    0.74
    Inverse
    0.70
    Activations Density 2.265%

    No Known Activations