© 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. 146
    Prev
    Next
    INDEX
    Explanations

    locations and descriptions of violent events

    oai_token-act-pair · gemini-2.0-flash

    News or technical articles

    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
     beach
    -1.70
     coastal
    -1.65
     marine
    -1.61
     seawater
    -1.61
     maritime
    -1.58
     ocean
    -1.57
    Beach
    -1.56
     sea
    -1.55
     Beach
    -1.55
     seaside
    -1.55
    POSITIVE LOGITS
    expandindo
    0.52
     otomatig
    0.47
     estekak
    0.45
    AssignableFrom
    0.43
    Autoritní
    0.43
     GenerationType
    0.43
     Taktlose
    0.41
    település
    0.40
    єра
    0.40
     FBref
    0.40
    Activations Density 63.269%

    No Known Activations