© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62834
    Prev
    Next
    INDEX
    Explanations

    destroying, destruction, breaking, or smashing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
    છ
    0.37
    cosx
    0.36
    戍
    0.35
    ometrical
    0.34
    blkid
    0.34
    icioso
    0.34
    Goss
    0.34
    餉
    0.34
    }.\
    0.34
    /-}$
    0.33
    POSITIVE LOGITS
     разру
    1.69
     destroyed
    1.68
     destruction
    1.66
     destroy
    1.57
     Destroy
    1.57
    破壊
    1.57
     destruir
    1.54
     destroying
    1.52
     destru
    1.52
     destroys
    1.50
    Activations Density 0.066%

    No Known Activations