© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14844
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are emphasized, capitalized, or otherwise stand out

    oai_token-act-pair · gemini-2.0-flash

    Negative or strong opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     EXISTING
    -0.94
     RESULTS
    -0.93
     FOURTH
    -0.93
     PRIMARY
    -0.91
     QUALITY
    -0.86
     ANNUAL
    -0.86
     ADVERTISING
    -0.85
     AIRCRAFT
    -0.83
     CLINICAL
    -0.83
     PREVIOUS
    -0.83
    POSITIVE LOGITS
     SE
    0.94
     TR
    0.90
     BR
    0.84
     AR
    0.82
     IS
    0.81
     CR
    0.80
     MIS
    0.79
     SU
    0.79
     IM
    0.78
     ME
    0.78
    Activations Density 3.275%

    No Known Activations