© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 787
    Prev
    Next
    INDEX
    Explanations

    words associated with government, education, and workplace conflict, especially those that suggest power dynamics and legal processes.

    oai_token-act-pair · gemini-2.0-flash

    Web pages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    towards
    -1.68
     towards
    -1.66
     Towards
    -1.45
    Towards
    -1.35
     judgement
    -1.02
     outwards
    -0.98
     internet
    -0.98
    wards
    -0.98
     grey
    -0.94
     downwards
    -0.92
    POSITIVE LOGITS
     Web
    0.83
    Web
    0.49
    шан
    0.43
    </h3>
    0.42
    </h5>
    0.39
    ThemeOverlay
    0.39
     quá
    0.38
     sepa
    0.38
    quark
    0.37
    ]<<"
    0.37
    Activations Density 5.301%

    No Known Activations