© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6278
    Prev
    Next
    INDEX
    Explanations

    statements from the police in the context of political demonstrations or labor disputes.

    oai_token-act-pair · gemini-2.0-flash

    formal recognition terms

    np_token-act-pair-logits · gpt-4o-mini

    unions workers politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ibatis
    -0.48
     الرياضيه
    -0.39
    LookAnd
    -0.39
     Jurassic
    -0.39
    onActivityResult
    -0.37
     Morse
    -0.36
    jface
    -0.35
    ījum
    -0.35
    }();
    -0.34
     pin
    -0.34
    POSITIVE LOGITS
    DoubleQuotes
    0.85
     يتيمه
    0.74
    \{\\
    0.74
     defaultstate
    0.73
    InjectAttribute
    0.73
     MainAxisSize
    0.73
    Tembelea
    0.71
    LLocation
    0.70
     تانيه
    0.67
    swick
    0.66
    Activations Density 0.807%

    No Known Activations