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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8346
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations associated with tumors and their treatment

    oai_token-act-pair · gemini-2.0-flash

    lipMethod: 1Reason: No pattern could be determined.lip

    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
     colors
    -2.22
     color
    -2.22
     colored
    -2.09
     favorite
    -2.08
     behavior
    -2.06
     labor
    -2.06
     flavors
    -2.05
     Ее
    -2.05
     neighbors
    -2.03
     favor
    -2.02
    POSITIVE LOGITS
    SaveChangesAsync
    0.63
     doInBackground
    0.59
    aturi
    0.59
    printList
    0.55
     Wikimedijinoj
    0.55
     Audiodateien
    0.53
    InstanceState
    0.53
    !(:
    0.52
    øver
    0.52
    endpush
    0.51
    Activations Density 4.305%

    No Known Activations