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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1920
    Prev
    Next
    INDEX
    Explanations

    sending condolences

    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_40_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
     Hakk
    0.24
     executed
    0.24
     interest
    0.24
     intérêt
    0.23
    짬
    0.23
     căn
    0.23
    ментом
    0.23
    メタル
    0.23
    柒
    0.23
     Interessen
    0.22
    POSITIVE LOGITS
     dtype
    0.22
     type
    0.22
     guards
    0.22
    âmica
    0.22
    estal
    0.22
     forwarded
    0.22
    ニュアル
    0.22
    coordinates
    0.22
     roar
    0.22
    לא
    0.22
    Activations Density 0.007%

    No Known Activations