© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13035
    Prev
    Next
    INDEX
    Explanations

    legal and academic language

    oai_token-act-pair · gemini-2.0-flash

    Official titles and positions

    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
    president
    -1.06
     president
    -1.02
     senator
    -0.90
     governor
    -0.89
     archbishop
    -0.88
    governor
    -0.86
     chancellor
    -0.85
    professor
    -0.83
     bishop
    -0.80
     vice
    -0.79
    POSITIVE LOGITS
     kasarigan
    0.40
    RegressionTest
    0.40
    anim
    0.37
     flor
    0.37
     dig
    0.36
    lit
    0.35
     grit
    0.35
     bet
    0.35
    arg
    0.35
     gri
    0.35
    Activations Density 5.462%

    No Known Activations