© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14392
    Prev
    Next
    INDEX
    Explanations

    words related to psychological and physiological disorders and the names of medical studies

    oai_token-act-pair · gemini-2.0-flash

    Biology/medical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     makers
    -0.52
     insertion
    -0.51
     insertions
    -0.50
     plu
    -0.50
     PLS
    -0.49
     HV
    -0.49
     clad
    -0.49
     VT
    -0.49
     Ouvrez
    -0.48
     nakalista
    -0.48
    POSITIVE LOGITS
     ويكيميديا
    0.62
    الإنجليزية
    0.58
    eip
    0.53
     }{@
    0.48
    onOptions
    0.48
    DeleteBehavior
    0.47
    BeginContext
    0.47
    logisch
    0.47
    хьтан
    0.46
    ographiques
    0.45
    Activations Density 4.952%

    No Known Activations