© 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. 5626
    Prev
    Next
    INDEX
    Explanations

    places, people or events that are newsworthy, or related to conflict or politics.

    oai_token-act-pair · gemini-2.0-flash

    war and peace

    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
    Mesh
    -0.56
    fxml
    -0.55
    reactivex
    -0.55
    WithIOException
    -0.50
     cref
    -0.50
     Cientí
    -0.50
    Xna
    -0.50
     financière
    -0.50
    IContainer
    -0.49
     Insee
    -0.49
    POSITIVE LOGITS
    énéral
    0.52
     Rebellion
    0.52
    ])]
    0.49
     terror
    0.49
    !<
    0.48
     Roskov
    0.47
    following
    0.47
     "}";
    0.46
    "]).
    0.45
    !")
    
    0.45
    Activations Density 27.381%

    No Known Activations