© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204676
    Prev
    Next
    INDEX
    Explanations

    good

    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_46_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
     والغ
    0.36
    BAD
    0.34
     स्टोक्स
    0.34
    BadRequest
    0.34
    Bad
    0.33
     Bad
    0.33
     बद
    0.33
    ଳ
    0.33
     finest
    0.32
    糟糕
    0.32
    POSITIVE LOGITS
     good
    2.83
    good
    2.52
     хоро
    2.14
    Good
    2.11
     buona
    2.09
     goede
    2.08
     buena
    2.05
     Good
    2.02
     gute
    2.02
     buenas
    1.97
    Activations Density 0.029%

    No Known Activations