© 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. 15111
    Prev
    Next
    INDEX
    Explanations

    words related to the liver and/or breasts and related medical terms

    oai_token-act-pair · gemini-2.0-flash

    heart or liver

    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
    ModelSerializer
    -0.65
     Roskov
    -0.60
    ьаж
    -0.57
    enderror
    -0.51
    Rüyada
    -0.50
    IntoConstraints
    -0.49
     विश्वसनीयता
    -0.49
    ίδι
    -0.48
     Hercules
    -0.47
     PrintWriter
    -0.47
    POSITIVE LOGITS
    Hochspringen
    0.58
    ều
    0.56
    InputBorder
    0.53
     defaultstate
    0.53
    ImageContext
    0.50
     Privacidade
    0.50
     Ανακτήθηκε
    0.49
    JsonProperty
    0.48
    WEBPACK
    0.47
    cokinetic
    0.47
    Activations Density 4.649%

    No Known Activations