© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80304
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    eezy
    0.39
     அருள்
    0.37
     ಅಥವಾ
    0.37
     outbound
    0.36
    ዝ
    0.36
     orbifold
    0.36
     দক্ষ
    0.35
     তুল
    0.35
    ногие
    0.35
    入境
    0.35
    POSITIVE LOGITS
    thia
    0.43
    Ri
    0.43
    ුණු
    0.38
    病的
    0.37
    哃
    0.36
    RK
    0.35
    //}
    0.35
    ongs
    0.35
    ifed
    0.35
    㕷
    0.35
    Activations Density 0.001%

    No Known Activations