© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215876
    Prev
    Next
    INDEX
    Explanations

    BULLET, json, files, group, toad

    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_16_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
    bfs
    0.52
    s
    0.48
    facial
    0.45
     लिहा
    0.44
    valent
    0.42
    bing
    0.42
     جمله
    0.41
    Š
    0.41
    fon
    0.41
    ribe
    0.41
    POSITIVE LOGITS
    يط
    0.55
     randomize
    0.50
     doodle
    0.49
     apoi
    0.49
     UNION
    0.49
     colo
    0.49
    يت
    0.48
     następnie
    0.47
     Quick
    0.47
     Inverness
    0.47
    Activations Density 0.000%

    No Known Activations