© 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. 1105
    Prev
    Next
    INDEX
    Explanations

    sequences that look like citations, especially those referring to medical research, in addition to contract numbers and formal legal language.

    oai_token-act-pair · gemini-2.0-flash

    technical writing snippets

    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
    0
    -0.89
    ０
    -0.65
     betweenstory
    -0.65
    createCell
    -0.59
     lenker
    -0.59
     للمعارف
    -0.56
    Personensuche
    -0.56
    لينكات
    -0.56
     ۰
    -0.55
     bezeichneter
    -0.54
    POSITIVE LOGITS
    z
    0.54
     Bh
    0.53
    SF
    0.52
    sk
    0.48
    zf
    0.48
    FTS
    0.47
    etz
    0.47
    苷
    0.47
    WriteAttribute
    0.47
    FE
    0.46
    Activations Density 3.153%

    No Known Activations