© 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. 3643
    Prev
    Next
    INDEX
    Explanations

    jealousy and greedy

    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
     Madonna
    1.87
     shock
    1.87
    い
    1.81
     reassure
    1.80
    $\--
    1.78
     traumatic
    1.78
     möjlig
    1.77
     baptism
    1.76
     responders
    1.76
     TDI
    1.76
    POSITIVE LOGITS
    есть
    1.85
    expensive
    1.67
    orn
    1.65
    \{
    1.61
    п
    1.57
    एं
    1.51
    cwd
    1.49
    OL
    1.49
    ই
    1.48
    త
    1.48
    Activations Density 0.037%

    No Known Activations