© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121265
    Prev
    Next
    INDEX
    Explanations

    descending order or down

    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_38_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
     올라
    1.02
     upload
    0.99
    升
    0.99
     yüks
    0.98
    upload
    0.96
     Upload
    0.94
     uploading
    0.94
    Asc
    0.93
     asc
    0.92
     ascended
    0.92
    POSITIVE LOGITS
     down
    1.46
     turun
    1.42
     Down
    1.40
    降
    1.38
    down
    1.37
    Down
    1.36
     내려
    1.36
    ลง
    1.34
     descend
    1.34
     DOWN
    1.34
    Activations Density 0.003%

    No Known Activations