© 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. 8973
    Prev
    Next
    INDEX
    Explanations

    dates, locations and prepositions.

    oai_token-act-pair · gemini-2.0-flash

    municipality

    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
    OFFICE
    -0.65
    office
    -0.65
     office
    -0.63
    Office
    -0.59
    Gc
    -0.58
     OFFICE
    -0.56
     Office
    -0.56
     Hall
    -0.52
    UNCIL
    -0.51
     hall
    -0.51
    POSITIVE LOGITS
     City
    1.75
    City
    1.52
     CITY
    1.41
     Town
    1.17
    CITY
    1.15
    city
    1.14
     city
    1.10
    Town
    1.01
     TOWN
    0.88
     Stadt
    0.88
    Activations Density 4.919%

    No Known Activations