© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 201597
    Prev
    Next
    INDEX
    Explanations

    The Rings of Power

    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_12_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
    irit
    0.48
     p
    0.47
    !</
    0.44
     ठीक
    0.43
     drank
    0.43
    aan
    0.42
     אין
    0.41
     उन्हें
    0.41
    tid
    0.41
    giờ
    0.41
    POSITIVE LOGITS
    шего
    0.46
     employment
    0.46
     germination
    0.46
     Selon
    0.45
    ຍ
    0.45
    нера
    0.44
     valor
    0.43
     businesswoman
    0.42
     calorimetric
    0.42
     perí
    0.42
    Activations Density 0.001%

    No Known Activations