© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3607
    Prev
    Next
    INDEX
    Explanations

    even more [adjective]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unlike
    2.13
    mêmes
    2.11
    ➧
    2.10
    
    2.01
     avete
    1.96
     applicationId
    1.96
     "./
    1.95
    ◙
    1.95
     tolerate
    1.95
     bedtime
    1.92
    POSITIVE LOGITS
    an
    1.86
    й
    1.85
    ت
    1.80
    де
    1.77
    چه
    1.75
    йга
    1.74
    не
    1.59
    ли
    1.58
    ine
    1.57
    фи
    1.55
    Activations Density 0.028%

    No Known Activations