© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14614
    Prev
    Next
    INDEX
    Explanations

    mentions of military actions and their consequences

    oai_token-act-pair · gemini-2.0-flash

    say boat/ship

    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
     ship
    -1.46
    ship
    -1.33
    Ship
    -1.29
     Ship
    -1.26
     SHIP
    -1.12
    SHIP
    -0.99
     boat
    -0.94
     plane
    -0.93
     vessel
    -0.93
    boat
    -0.86
    POSITIVE LOGITS
     defaultstate
    0.68
     fri
    0.62
    EndGlobalSection
    0.60
     الحره
    0.59
     препратки
    0.54
    Viitteet
    0.54
     pymysql
    0.53
    Facades
    0.52
     **)
    0.51
    ----</
    0.50
    Activations Density 6.114%

    No Known Activations