© 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. 10044
    Prev
    Next
    INDEX
    Explanations

    legal documents and dating profiles, specifically looking for honesty, caring, love, and kindness.

    oai_token-act-pair · gemini-2.0-flash

    Technical documents

    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
    berdayakan
    -0.87
     nôtre
    -0.81
     rêves
    -0.79
     stället
    -0.79
     prisonniers
    -0.78
     genoux
    -0.75
     fumée
    -0.74
     découver
    -0.74
     hâte
    -0.73
     larmes
    -0.73
    POSITIVE LOGITS
     thorium
    0.56
     thrush
    0.53
     monoxide
    0.53
     benthic
    0.52
     serpentine
    0.52
     tetanus
    0.52
     turbidity
    0.52
     tidal
    0.52
     gazelle
    0.52
     axial
    0.52
    Activations Density 3.332%

    No Known Activations