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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4178
    Prev
    Next
    INDEX
    Explanations

    words or phrases in a medical or scientific context that describe a condition or process and its related qualities.

    oai_token-act-pair · gemini-2.0-flash

    related to diabetes/insulin

    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
     Roskov
    -0.66
    })`
    -0.59
     Cæsar
    -0.50
     endregion
    -0.50
     pinulongan
    -0.50
     PyTuple
    -0.49
    VolleyError
    -0.47
     borough
    -0.47
    RTSC
    -0.47
     gustó
    -0.46
    POSITIVE LOGITS
     single
    0.53
     availability
    0.52
    bones
    0.50
    ibly
    0.50
    jestel
    0.50
    plotly
    0.50
    gherita
    0.50
    __':
    0.50
     cost
    0.49
    ificantly
    0.49
    Activations Density 2.220%

    No Known Activations