© 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. 12882
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terminology, particularly related to anatomical terms, diseases, and chemical compounds.

    oai_token-act-pair · gemini-2.0-flash

    Ben

    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
    cmath
    -0.45
     Oates
    -0.45
     Auß
    -0.45
    vician
    -0.44
     Mudd
    -0.42
     DTM
    -0.42
     Molière
    -0.42
    ulipas
    -0.42
     resourceCulture
    -0.40
     Monark
    -0.40
    POSITIVE LOGITS
     BEN
    1.25
     Ben
    1.20
    Ben
    1.13
     Bens
    1.12
     ben
    1.08
    ens
    1.08
    ento
    1.08
    BEN
    1.08
    ENS
    1.06
     Bench
    1.06
    Activations Density 5.342%

    No Known Activations