© 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. 8544
    Prev
    Next
    INDEX
    Explanations

    text related to political disputes and treaties.

    oai_token-act-pair · gemini-2.0-flash

    historical documents

    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
     hoffe
    -0.54
    thâu
    -0.50
    Réalisation
    -0.47
     Jeffries
    -0.46
    ToBounds
    -0.46
     RequestMethod
    -0.46
     tantangan
    -0.46
     limitée
    -0.46
    InstanceState
    -0.46
     때문
    -0.45
    POSITIVE LOGITS
     nakalista
    0.61
    تقاوى
    0.59
    MigrationBuilder
    0.58
    Personensuche
    0.57
    awtextra
    0.54
    assertRaises
    0.52
     transfieras
    0.51
    BeginContext
    0.50
    govina
    0.49
    ])):
    0.49
    Activations Density 5.228%

    No Known Activations