© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166743
    Prev
    Next
    INDEX
    Explanations

    say ":"

    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_56_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
    大地
    0.37
    近平
    0.34
     hasilnya
    0.34
     greatest
    0.33
     fatt
    0.33
    Dev
    0.33
    =")"
    0.33
     äh
    0.32
    рі
    0.32
    aneously
    0.32
    POSITIVE LOGITS
    fxml
    0.39
     ->
    0.37
     ಸೂ
    0.36
    zess
    0.36
    -->
    0.36
    ->
    0.35
     করলো
    0.35
     acompaña
    0.34
     দেখিল
    0.34
     proto
    0.34
    Activations Density 0.002%

    No Known Activations