© 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. 9046
    Prev
    Next
    INDEX
    Explanations

    historical texts with battles, political structures, and deaths

    oai_token-act-pair · gemini-2.0-flash

    war, destruction

    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
    kloped
    -0.56
     BorderSide
    -0.55
    NamedQueries
    -0.50
    SequentialGroup
    -0.50
    permitAll
    -0.50
    phosa
    -0.48
     wipe
    -0.48
    🦵
    -0.47
    bangan
    -0.47
     def
    -0.47
    POSITIVE LOGITS
     שוליים
    0.68
    rungsseite
    0.65
    Bronnen
    0.60
    TestingModule
    0.60
    StoryboardSegue
    0.56
     Grecs
    0.56
     "..\..\..\
    0.54
    Hochspringen
    0.54
    uxxxx
    0.52
    новништво
    0.51
    Activations Density 4.195%

    No Known Activations